Pipeline run

{
  "final_skills": [
    {
      "is_primary": true,
      "skill_name": "Scala"
    },
    {
      "is_primary": true,
      "skill_name": "Maven"
    },
    {
      "is_primary": true,
      "skill_name": "Apache Spark"
    },
    {
      "is_primary": true,
      "skill_name": "Unix Shell Scripting"
    },
    {
      "is_primary": true,
      "skill_name": "Unix"
    },
    {
      "is_primary": true,
      "skill_name": "HDFS"
    },
    {
      "is_primary": true,
      "skill_name": "Oracle SQL"
    },
    {
      "is_primary": true,
      "skill_name": "Hive SQL"
    },
    {
      "is_primary": true,
      "skill_name": "Spark SQL"
    },
    {
      "is_primary": true,
      "skill_name": "Impala"
    },
    {
      "is_primary": true,
      "skill_name": "HBase"
    },
    {
      "is_primary": true,
      "skill_name": "CI/CD"
    },
    {
      "is_primary": true,
      "skill_name": "Hive"
    }
  ],
  "jd_role": {
    "display_name": "BigData Developer",
    "rationale": null,
    "role_aliases": [
      "Big Data Engineer",
      "Big Data Developer",
      "Data Engineer"
    ],
    "role_archetype": "Engineering",
    "slug": ""
  },
  "nano_parsed": {
    "JD_type": "pass",
    "about_company": null,
    "certifications": [],
    "company_name": "TCS",
    "ctc": null,
    "domain": {
      "primary": {
        "aliases": [
          "ITES",
          "BPO",
          "Tech Consulting"
        ],
        "domain": "IT Services \u0026 Consulting"
      },
      "secondary": null
    },
    "education": [],
    "experience": {
      "max": 8,
      "min": 3,
      "raw": "3 to 8 years"
    },
    "job_locations": [
      {
        "aliases": [],
        "city": "Chennai",
        "country": null,
        "state": null,
        "work_mode": null
      },
      {
        "aliases": [],
        "city": "Hyderabad",
        "country": null,
        "state": null,
        "work_mode": null
      },
      {
        "aliases": [
          "Bengaluru"
        ],
        "city": "Bangalore",
        "country": null,
        "state": null,
        "work_mode": null
      },
      {
        "aliases": [],
        "city": "Pune",
        "country": null,
        "state": null,
        "work_mode": null
      },
      {
        "aliases": [
          "Calcutta"
        ],
        "city": "Kolkata",
        "country": null,
        "state": null,
        "work_mode": null
      }
    ],
    "role": "BigData Developer",
    "role_aliases": [
      "Big Data Engineer",
      "Big Data Developer",
      "Data Engineer"
    ],
    "role_archetype": "Engineering",
    "roles_and_responsibilities": [
      {
        "bullet_count": 5,
        "heading": "Must Have",
        "heading_was_present": true,
        "source_marker": {
          "first_5_words": "\u2022 Hands on development experience",
          "last_5_words": "communication and customer management skills"
        },
        "text": "\u2022 Hands on development experience in programming languages such as SCALA using Maven, Apache Spark Frameworks and Unix Shell scripting \n\u2022 Should be comfortable with Unix File system as well as HDFS commands \n\u2022 Should have worked on query languages such as Oracle SQL, Hive SQL, Spark SQL, Impala, HBase DB \n\u2022 Should be flexible \n\u2022 Should have good communication and customer management skills",
        "word_count": 51
      },
      {
        "bullet_count": 4,
        "heading": "Roles and Responsibilities",
        "heading_was_present": true,
        "source_marker": {
          "first_5_words": "\u2022 Design high quality deliverables",
          "last_5_words": "data transformation solutions , Hive"
        },
        "text": "\u2022 Design high quality deliverables adhering to business requirement with defined standards and design principles, patterns\n\u2022 Develop and maintain highly scalable, high performance Data transformation applications using Apache Spark framework\n\u2022 Develop/Integrate the code adhering to CI/CD, using Spark Framework in Scala\n\u2022 Provide solutions to Big data problems dealing with huge volumes of data using Spark based data transformation solutions , Hive",
        "word_count": 64
      }
    ],
    "urls": []
  },
  "rejected": false,
  "rejection_reason": null,
  "run_id": "9bd37876-38fa-4481-9ba5-d79d3dc251b3",
  "stage3_signals": {
    "alias_found": true,
    "alias_match_roles": [
      {
        "display_name": "Data Engineer",
        "kra_matches": null,
        "matched_count": null,
        "matched_skills": null,
        "role_id": 2,
        "score": 1.0,
        "slug": "data-engineer",
        "total_count": null
      }
    ],
    "kra_match_roles": [
      {
        "display_name": "Data Engineer",
        "kra_matches": [
          {
            "kra_text": "Develops batch and real-time streaming data pipelines using Apache Spark, Apache Kafka, Apache Flink, or Airflow for data movement and processing at scale.",
            "sentence": "Develop and maintain highly scalable, high performance Data transformation applications using Apache Spark framework",
            "similarity": 0.6959
          },
          {
            "kra_text": "Develops batch and real-time streaming data pipelines using Apache Spark, Apache Kafka, Apache Flink, or Airflow for data movement and processing at scale.",
            "sentence": "Provide solutions to Big data problems dealing with huge volumes of data using Spark based data transformation solutions , Hive",
            "similarity": 0.5986
          },
          {
            "kra_text": "Develops batch and real-time streaming data pipelines using Apache Spark, Apache Kafka, Apache Flink, or Airflow for data movement and processing at scale.",
            "sentence": "Develop/Integrate the code adhering to CI/CD, using Spark Framework in Scala",
            "similarity": 0.5424
          }
        ],
        "matched_count": null,
        "matched_skills": null,
        "role_id": 2,
        "score": 0.6123,
        "slug": "data-engineer",
        "total_count": null
      },
      {
        "display_name": "Fullstack Developer",
        "kra_matches": [
          {
            "kra_text": "Designs and queries relational databases like PostgreSQL and document stores like MongoDB, writing migrations, indexes, and optimized queries.",
            "sentence": "Should have worked on query languages such as Oracle SQL, Hive SQL, Spark SQL, Impala, HBase DB",
            "similarity": 0.5044
          },
          {
            "kra_text": "Works closely with product managers and UX designers to translate requirements and wireframes into working software features through iterative development.",
            "sentence": "Design high quality deliverables adhering to business requirement with defined standards and design principles, patterns",
            "similarity": 0.4794
          },
          {
            "kra_text": "Designs and queries relational databases like PostgreSQL and document stores like MongoDB, writing migrations, indexes, and optimized queries.",
            "sentence": "Develop and maintain highly scalable, high performance Data transformation applications using Apache Spark framework",
            "similarity": 0.4336
          }
        ],
        "matched_count": null,
        "matched_skills": null,
        "role_id": 15,
        "score": 0.4725,
        "slug": "full-stack-engineer",
        "total_count": null
      },
      {
        "display_name": "ML Engineer",
        "kra_matches": [
          {
            "kra_text": "Prepares, cleans, and transforms training datasets, manages feature stores, and builds feature engineering pipelines for model training.",
            "sentence": "Develop and maintain highly scalable, high performance Data transformation applications using Apache Spark framework",
            "similarity": 0.4859
          },
          {
            "kra_text": "Prepares, cleans, and transforms training datasets, manages feature stores, and builds feature engineering pipelines for model training.",
            "sentence": "Provide solutions to Big data problems dealing with huge volumes of data using Spark based data transformation solutions , Hive",
            "similarity": 0.4503
          },
          {
            "kra_text": "Translates product requirements into machine learning system specifications including feature definitions, model architecture choices, and success metric definitions.",
            "sentence": "Design high quality deliverables adhering to business requirement with defined standards and design principles, patterns",
            "similarity": 0.3963
          }
        ],
        "matched_count": null,
        "matched_skills": null,
        "role_id": 3,
        "score": 0.4442,
        "slug": "ml-engineer",
        "total_count": null
      },
      {
        "display_name": "Angular Frontend Developer",
        "kra_matches": [
          {
            "kra_text": "collaboration with design and QA",
            "sentence": "Design high quality deliverables adhering to business requirement with defined standards and design principles, patterns",
            "similarity": 0.5011
          },
          {
            "kra_text": "code review and refactoring",
            "sentence": "Develop/Integrate the code adhering to CI/CD, using Spark Framework in Scala",
            "similarity": 0.4346
          },
          {
            "kra_text": "code review and refactoring",
            "sentence": "Hands on development experience in programming languages such as SCALA using Maven, Apache Spark Frameworks and Unix Shell scripting",
            "similarity": 0.3626
          }
        ],
        "matched_count": null,
        "matched_skills": null,
        "role_id": 90,
        "score": 0.4328,
        "slug": "angular-frontend-developer",
        "total_count": null
      },
      {
        "display_name": "Backend Developer",
        "kra_matches": [
          {
            "kra_text": "Writes database access logic including SQL queries, ORM mappings, stored procedures, and migration scripts for relational databases like PostgreSQL and MySQL.",
            "sentence": "Should have worked on query languages such as Oracle SQL, Hive SQL, Spark SQL, Impala, HBase DB",
            "similarity": 0.4447
          },
          {
            "kra_text": "Identifies and resolves backend performance bottlenecks through query optimization, indexing strategies, connection pooling, and distributed caching with Redis.",
            "sentence": "Develop and maintain highly scalable, high performance Data transformation applications using Apache Spark framework",
            "similarity": 0.4193
          },
          {
            "kra_text": "Integrates with third-party services, payment gateways, messaging queues like Kafka or RabbitMQ, and internal microservices via HTTP and event-driven patterns.",
            "sentence": "Develop/Integrate the code adhering to CI/CD, using Spark Framework in Scala",
            "similarity": 0.4159
          }
        ],
        "matched_count": null,
        "matched_skills": null,
        "role_id": 1,
        "score": 0.4266,
        "slug": "backend-engineer",
        "total_count": null
      }
    ],
    "skill_match_roles": [
      {
        "display_name": "DevOps Engineer",
        "kra_matches": null,
        "matched_count": 2,
        "matched_skills": [
          "CI/CD",
          "Maven"
        ],
        "role_id": 10,
        "score": 0.1538,
        "slug": "devops-engineer",
        "total_count": 13
      },
      {
        "display_name": "Data Engineer",
        "kra_matches": null,
        "matched_count": 2,
        "matched_skills": [
          "Apache Spark",
          "Scala"
        ],
        "role_id": 2,
        "score": 0.1538,
        "slug": "data-engineer",
        "total_count": 13
      },
      {
        "display_name": "ML Engineer",
        "kra_matches": null,
        "matched_count": 2,
        "matched_skills": [
          "CI/CD",
          "Scala"
        ],
        "role_id": 3,
        "score": 0.1538,
        "slug": "ml-engineer",
        "total_count": 13
      },
      {
        "display_name": "Cloud Architect",
        "kra_matches": null,
        "matched_count": 1,
        "matched_skills": [
          "HBase"
        ],
        "role_id": 9,
        "score": 0.0769,
        "slug": "cloud-architect",
        "total_count": 13
      },
      {
        "display_name": "iOS Developer",
        "kra_matches": null,
        "matched_count": 1,
        "matched_skills": [
          "Hive"
        ],
        "role_id": 6,
        "score": 0.0769,
        "slug": "ios-engineer",
        "total_count": 13
      }
    ]
  },
  "stage4_decision": {
    "alias_collision_detected": false,
    "case": "A",
    "chosen_role": {
      "display_name": "Data Engineer",
      "kra_matches": null,
      "matched_count": null,
      "matched_skills": null,
      "role_id": 2,
      "score": 1.0,
      "slug": "data-engineer",
      "total_count": null
    },
    "confidence": 1.0,
    "is_new_role": false,
    "llm2_fired": false,
    "llm2_reasoning": null,
    "matched_dimensions": [],
    "matched_kras": [],
    "matched_skills": [],
    "new_role_display_name": null,
    "new_role_slug": null,
    "queued": false,
    "reasoning": "Exact alias hit on data-engineer (1.0) \u2014 no other alias at this confidence; skill_top devops-engineer 0.15 does not contradict",
    "sub_role": null
  },
  "stage5_updates": {
    "centroid_n_after": 454,
    "centroid_updated": true,
    "collision_log_id": null,
    "new_kra_attached": null,
    "new_skills_attached": [
      {
        "is_primary": true,
        "queue_id": 21060,
        "role_display_name": "Data Engineer",
        "role_slug": "data-engineer",
        "skill_name": "Unix Shell Scripting",
        "status": "pending"
      },
      {
        "is_primary": true,
        "queue_id": 21061,
        "role_display_name": "Data Engineer",
        "role_slug": "data-engineer",
        "skill_name": "Unix",
        "status": "pending"
      },
      {
        "is_primary": true,
        "queue_id": 21062,
        "role_display_name": "Data Engineer",
        "role_slug": "data-engineer",
        "skill_name": "HDFS",
        "status": "pending"
      },
      {
        "is_primary": true,
        "queue_id": 21063,
        "role_display_name": "Data Engineer",
        "role_slug": "data-engineer",
        "skill_name": "Oracle SQL",
        "status": "pending"
      },
      {
        "is_primary": true,
        "queue_id": 21064,
        "role_display_name": "Data Engineer",
        "role_slug": "data-engineer",
        "skill_name": "Hive SQL",
        "status": "pending"
      },
      {
        "is_primary": true,
        "queue_id": 21065,
        "role_display_name": "Data Engineer",
        "role_slug": "data-engineer",
        "skill_name": "Spark SQL",
        "status": "pending"
      },
      {
        "is_primary": true,
        "queue_id": 21066,
        "role_display_name": "Data Engineer",
        "role_slug": "data-engineer",
        "skill_name": "Impala",
        "status": "pending"
      }
    ],
    "queue_entry_id": null,
    "v3_pipeline_triggered": false,
    "v3_role_slug": null,
    "v3_run_id": null
  }
}

{
  "alias_matches": [
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 272,
      "existing_alias_text": "Scala",
      "input_term": "Scala",
      "matched_canonical": {
        "category_id": 6,
        "display_name": "Scala",
        "id": 102,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "LANGUAGE",
        "slug": "scala",
        "sub_category_id": 96,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 1360,
      "existing_alias_text": "Maven",
      "input_term": "Maven",
      "matched_canonical": {
        "category_id": 13,
        "display_name": "Maven",
        "id": 815,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "TOOL",
        "slug": "maven",
        "sub_category_id": 358,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 2004,
      "existing_alias_text": "Apache Spark",
      "input_term": "Apache Spark",
      "matched_canonical": {
        "category_id": 5,
        "display_name": "Apache Spark",
        "id": 1350,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "FRAMEWORK",
        "slug": "apache-spark",
        "sub_category_id": 1021,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "TODO: REMOVE AFTER TESTING \u2014 alias DB write disabled",
      "alias_persisted": false,
      "existing_alias_id": 2512,
      "existing_alias_text": "Oracle Database",
      "input_term": "Oracle SQL",
      "matched_canonical": {
        "category_id": 3,
        "display_name": "Oracle Database",
        "id": 1566,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "TOOL",
        "slug": "oracle-database",
        "sub_category_id": 29,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "embedding_alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 2011,
      "existing_alias_text": "HBase",
      "input_term": "HBase",
      "matched_canonical": {
        "category_id": 3,
        "display_name": "HBase",
        "id": 1352,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "TOOL",
        "slug": "hbase",
        "sub_category_id": 31,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 1826,
      "existing_alias_text": "CI/CD",
      "input_term": "CI/CD",
      "matched_canonical": {
        "category_id": 8,
        "display_name": "CI/CD",
        "id": 1190,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "METHODOLOGY",
        "slug": "ci-cd",
        "sub_category_id": 900,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 4198,
      "existing_alias_text": "Hive",
      "input_term": "Hive",
      "matched_canonical": {
        "category_id": 3,
        "display_name": "Hive",
        "id": 2754,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "TOOL",
        "slug": "hive",
        "sub_category_id": 2242,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    }
  ],
  "candidate_roles": [
    {
      "display_name": "Data Engineer",
      "id": 2,
      "rationale": null,
      "role_archetype": null,
      "slug": "data-engineer",
      "source": "db"
    },
    {
      "display_name": "ML Engineer",
      "id": 3,
      "rationale": null,
      "role_archetype": null,
      "slug": "ml-engineer",
      "source": "db"
    },
    {
      "display_name": "MLOps Engineer",
      "id": 16,
      "rationale": null,
      "role_archetype": null,
      "slug": "ml-ops-engineer",
      "source": "db"
    },
    {
      "display_name": "Java Backend Developer",
      "id": 79,
      "rationale": null,
      "role_archetype": "Engineering",
      "slug": "java-backend-developer",
      "source": "db"
    },
    {
      "display_name": "DevOps Engineer",
      "id": 10,
      "rationale": null,
      "role_archetype": null,
      "slug": "devops-engineer",
      "source": "db"
    },
    {
      "display_name": "Ionic Developer",
      "id": 434,
      "rationale": null,
      "role_archetype": null,
      "slug": "ionic-developer",
      "source": "db"
    },
    {
      "display_name": ".NET Backend Developer",
      "id": 83,
      "rationale": null,
      "role_archetype": "Engineering",
      "slug": "dotnet-backend-developer",
      "source": "db"
    },
    {
      "display_name": "Backend Developer",
      "id": 1,
      "rationale": null,
      "role_archetype": "A Backend Engineer designs, builds, and maintains the server-side logic and data handling that power applications and services. They focus on implementing reliable business functionality, integrating with other systems, and ensuring the backend is scalable, maintainable, and observable.",
      "slug": "backend-engineer",
      "source": "db"
    },
    {
      "display_name": "Kotlin Backend Developer",
      "id": 84,
      "rationale": null,
      "role_archetype": "Engineering",
      "slug": "kotlin-server-backend-developer",
      "source": "db"
    },
    {
      "display_name": "Node.js Backend Developer",
      "id": 82,
      "rationale": null,
      "role_archetype": "Engineering",
      "slug": "node-backend-developer",
      "source": "db"
    },
    {
      "display_name": "Python Backend Developer",
      "id": 80,
      "rationale": null,
      "role_archetype": "Engineering",
      "slug": "python-backend-developer",
      "source": "db"
    },
    {
      "display_name": "Ruby Backend Developer",
      "id": 85,
      "rationale": null,
      "role_archetype": "Engineering",
      "slug": "ruby-backend-developer",
      "source": "db"
    },
    {
      "display_name": "Scala Backend Developer",
      "id": 87,
      "rationale": null,
      "role_archetype": "Engineering",
      "slug": "scala-backend-developer",
      "source": "db"
    },
    {
      "display_name": "Cloud Architect",
      "id": 9,
      "rationale": null,
      "role_archetype": null,
      "slug": "cloud-architect",
      "source": "db"
    },
    {
      "display_name": "Android Developer",
      "id": 4,
      "rationale": null,
      "role_archetype": null,
      "slug": "android-engineer",
      "source": "db"
    },
    {
      "display_name": "Flutter Developer",
      "id": 74,
      "rationale": null,
      "role_archetype": "Engineering",
      "slug": "flutter-developer",
      "source": "db"
    },
    {
      "display_name": "Hybrid Mobile Developer",
      "id": 11,
      "rationale": null,
      "role_archetype": null,
      "slug": "hybrid-mobile-developer",
      "source": "db"
    },
    {
      "display_name": "Native Mobile Developer",
      "id": 75,
      "rationale": null,
      "role_archetype": "Engineering",
      "slug": "native-mobile-developer",
      "source": "db"
    },
    {
      "display_name": "React Native Developer",
      "id": 73,
      "rationale": null,
      "role_archetype": "Engineering",
      "slug": "react-native-developer",
      "source": "db"
    },
    {
      "display_name": "iOS Developer",
      "id": 6,
      "rationale": null,
      "role_archetype": null,
      "slug": "ios-engineer",
      "source": "db"
    }
  ],
  "chosen_role": {
    "display_name": "Data Engineer",
    "id": 2,
    "rationale": "Exact alias hit on data-engineer (1.0) \u2014 no other alias at this confidence; skill_top devops-engineer 0.15 does not contradict",
    "role_archetype": null,
    "slug": "data-engineer",
    "source": "db"
  },
  "dimensions": [
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Programming Languages for Data Work",
        "id": 21,
        "rationale": "Languages used to implement data pipelines, transformations, and operational glue. This is the primary coding surface for building ingestion, enrichment, and automation logic in data engineering.",
        "slug": "programming-languages-for-data-work",
        "source": "db"
      },
      "input_skill": "Scala",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Data Engineer",
          "id": 2,
          "rationale": null,
          "role_archetype": null,
          "slug": "data-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Programming Languages for ML Systems",
        "id": 39,
        "rationale": "Languages used to build training code, inference services, evaluation jobs, and ML glue code. This is the primary implementation surface for ML engineers across experimentation and productionization.",
        "slug": "programming-languages-for-ml-systems",
        "source": "db"
      },
      "input_skill": "Scala",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "ML Engineer",
          "id": 3,
          "rationale": null,
          "role_archetype": null,
          "slug": "ml-engineer",
          "source": "db"
        },
        {
          "display_name": "MLOps Engineer",
          "id": 16,
          "rationale": null,
          "role_archetype": null,
          "slug": "ml-ops-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Build and Dependency Management",
        "id": 286,
        "rationale": "Project build, packaging, and dependency resolution skills used to compile and assemble Java services. This cluster matters because backend delivery depends on reproducible builds and controlled library versions.",
        "slug": "build-and-dependency-management",
        "source": "db"
      },
      "input_skill": "Maven",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Java Backend Developer",
          "id": 79,
          "rationale": null,
          "role_archetype": "Engineering",
          "slug": "java-backend-developer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Build and Packaging Tooling",
        "id": 149,
        "rationale": "Tooling used to compile, package, and prepare Ionic apps for development and release. This cluster is coherent because Ionic developers often manage web assets, native wrappers, and environment-specific build outputs.",
        "slug": "build-and-packaging-tooling",
        "source": "db"
      },
      "input_skill": "Maven",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "DevOps Engineer",
          "id": 10,
          "rationale": null,
          "role_archetype": null,
          "slug": "devops-engineer",
          "source": "db"
        },
        {
          "display_name": "Ionic Developer",
          "id": 434,
          "rationale": null,
          "role_archetype": null,
          "slug": "ionic-developer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "ETL and ELT Tooling",
        "id": 24,
        "rationale": "Packaged tools for extracting, loading, and transforming data across systems. This dimension covers connector-based ingestion, transformation frameworks, and managed integration products.",
        "slug": "etl-and-elt-tooling",
        "source": "db"
      },
      "input_skill": "Apache Spark",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Data Engineer",
          "id": 2,
          "rationale": null,
          "role_archetype": null,
          "slug": "data-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "React Frontend Development",
        "id": 96,
        "rationale": "Building interactive web user interfaces with React.js, including component composition, state management, hooks, and rendering patterns. React.js belongs here because it is a core library for client-side UI development in modern web applications.",
        "slug": "d_init_01",
        "source": "db"
      },
      "input_skill": "Oracle SQL",
      "llm_role": null,
      "roles_from_db": []
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Relational Database Design",
        "id": 4,
        "rationale": "Modeling and operating relational persistence for backend services. Includes schema design, normalization, indexing, transactions, and query tuning for operational data stores.",
        "slug": "relational-database-design",
        "source": "db"
      },
      "input_skill": "Oracle SQL",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": ".NET Backend Developer",
          "id": 83,
          "rationale": null,
          "role_archetype": "Engineering",
          "slug": "dotnet-backend-developer",
          "source": "db"
        },
        {
          "display_name": "Backend Developer",
          "id": 1,
          "rationale": null,
          "role_archetype": "A Backend Engineer designs, builds, and maintains the server-side logic and data handling that power applications and services. They focus on implementing reliable business functionality, integrating with other systems, and ensuring the backend is scalable, maintainable, and observable.",
          "slug": "backend-engineer",
          "source": "db"
        },
        {
          "display_name": "Kotlin Backend Developer",
          "id": 84,
          "rationale": null,
          "role_archetype": "Engineering",
          "slug": "kotlin-server-backend-developer",
          "source": "db"
        },
        {
          "display_name": "Node.js Backend Developer",
          "id": 82,
          "rationale": null,
          "role_archetype": "Engineering",
          "slug": "node-backend-developer",
          "source": "db"
        },
        {
          "display_name": "Python Backend Developer",
          "id": 80,
          "rationale": null,
          "role_archetype": "Engineering",
          "slug": "python-backend-developer",
          "source": "db"
        },
        {
          "display_name": "Ruby Backend Developer",
          "id": 85,
          "rationale": null,
          "role_archetype": "Engineering",
          "slug": "ruby-backend-developer",
          "source": "db"
        },
        {
          "display_name": "Scala Backend Developer",
          "id": 87,
          "rationale": null,
          "role_archetype": "Engineering",
          "slug": "scala-backend-developer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Cloud Storage and Data Services",
        "id": 144,
        "rationale": "Cloud-native storage and managed data services used to place workloads, choose durability tiers, and define platform boundaries. This is a coherent cluster because architects evaluate storage fit, access patterns, and managed service tradeoffs.",
        "slug": "cloud-storage-and-data-services",
        "source": "db"
      },
      "input_skill": "HBase",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Cloud Architect",
          "id": 9,
          "rationale": null,
          "role_archetype": null,
          "slug": "cloud-architect",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "CI/CD Pipeline Platforms",
        "id": 150,
        "rationale": "Systems used to define, run, and maintain automated build and deployment workflows. This cluster is coherent because the role owns delivery automation end to end, including pipeline reliability and promotion logic.",
        "slug": "ci-cd-pipeline-platforms",
        "source": "db"
      },
      "input_skill": "CI/CD",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "DevOps Engineer",
          "id": 10,
          "rationale": null,
          "role_archetype": null,
          "slug": "devops-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "CI/CD for Machine Learning",
        "id": 56,
        "rationale": "Tools and platforms for automating ML model integration, testing, and deployment pipelines.",
        "slug": "ci-cd-for-machine-learning",
        "source": "db"
      },
      "input_skill": "CI/CD",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "ML Engineer",
          "id": 3,
          "rationale": null,
          "role_archetype": null,
          "slug": "ml-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Local Persistence and Offline Behavior",
        "id": 85,
        "rationale": "On-device storage used for caching, offline support, and durable client state. This cluster is coherent because iOS apps often need to preserve user progress and data when connectivity is limited.",
        "slug": "local-persistence-and-offline-behavior",
        "source": "db"
      },
      "input_skill": "Hive",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Android Developer",
          "id": 4,
          "rationale": null,
          "role_archetype": null,
          "slug": "android-engineer",
          "source": "db"
        },
        {
          "display_name": "Flutter Developer",
          "id": 74,
          "rationale": null,
          "role_archetype": "Engineering",
          "slug": "flutter-developer",
          "source": "db"
        },
        {
          "display_name": "Hybrid Mobile Developer",
          "id": 11,
          "rationale": null,
          "role_archetype": null,
          "slug": "hybrid-mobile-developer",
          "source": "db"
        },
        {
          "display_name": "Native Mobile Developer",
          "id": 75,
          "rationale": null,
          "role_archetype": "Engineering",
          "slug": "native-mobile-developer",
          "source": "db"
        },
        {
          "display_name": "React Native Developer",
          "id": 73,
          "rationale": null,
          "role_archetype": "Engineering",
          "slug": "react-native-developer",
          "source": "db"
        },
        {
          "display_name": "iOS Developer",
          "id": 6,
          "rationale": null,
          "role_archetype": null,
          "slug": "ios-engineer",
          "source": "db"
        }
      ]
    }
  ],
  "input_final_skills": [
    "Scala",
    "Maven",
    "Apache Spark",
    "Unix Shell Scripting",
    "Unix",
    "HDFS",
    "Oracle SQL",
    "Hive SQL",
    "Spark SQL",
    "Impala",
    "HBase",
    "CI/CD",
    "Hive"
  ],
  "input_llm_skills": [
    "Scala",
    "Maven",
    "Apache Spark",
    "Unix Shell Scripting",
    "Unix",
    "HDFS",
    "Oracle SQL",
    "Hive SQL",
    "Spark SQL",
    "Impala",
    "HBase",
    "CI/CD",
    "Hive"
  ],
  "new_aliases_persisted": 0,
  "run_id": "9bd37876-38fa-4481-9ba5-d79d3dc251b3",
  "skills_detail": [
    {
      "aliases_in_db": [
        {
          "alias_text": "Scala",
          "alias_type": "CANONICAL",
          "id": 272,
          "is_primary": true,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 6,
        "display_name": "Scala",
        "id": 102,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "LANGUAGE",
        "slug": "scala",
        "sub_category_id": 96,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Programming Languages for Data Work",
            "id": 21,
            "rationale": "Languages used to implement data pipelines, transformations, and operational glue. This is the primary coding surface for building ingestion, enrichment, and automation logic in data engineering.",
            "slug": "programming-languages-for-data-work",
            "source": "db"
          },
          "input_skill": "Scala",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Data Engineer",
              "id": 2,
              "rationale": null,
              "role_archetype": null,
              "slug": "data-engineer",
              "source": "db"
            }
          ]
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Programming Languages for ML Systems",
            "id": 39,
            "rationale": "Languages used to build training code, inference services, evaluation jobs, and ML glue code. This is the primary implementation surface for ML engineers across experimentation and productionization.",
            "slug": "programming-languages-for-ml-systems",
            "source": "db"
          },
          "input_skill": "Scala",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "ML Engineer",
              "id": 3,
              "rationale": null,
              "role_archetype": null,
              "slug": "ml-engineer",
              "source": "db"
            },
            {
              "display_name": "MLOps Engineer",
              "id": 16,
              "rationale": null,
              "role_archetype": null,
              "slug": "ml-ops-engineer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "Scala",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "Maven",
          "alias_type": "CANONICAL",
          "id": 1360,
          "is_primary": true,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 13,
        "display_name": "Maven",
        "id": 815,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "TOOL",
        "slug": "maven",
        "sub_category_id": 358,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Build and Dependency Management",
            "id": 286,
            "rationale": "Project build, packaging, and dependency resolution skills used to compile and assemble Java services. This cluster matters because backend delivery depends on reproducible builds and controlled library versions.",
            "slug": "build-and-dependency-management",
            "source": "db"
          },
          "input_skill": "Maven",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Java Backend Developer",
              "id": 79,
              "rationale": null,
              "role_archetype": "Engineering",
              "slug": "java-backend-developer",
              "source": "db"
            }
          ]
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Build and Packaging Tooling",
            "id": 149,
            "rationale": "Tooling used to compile, package, and prepare Ionic apps for development and release. This cluster is coherent because Ionic developers often manage web assets, native wrappers, and environment-specific build outputs.",
            "slug": "build-and-packaging-tooling",
            "source": "db"
          },
          "input_skill": "Maven",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "DevOps Engineer",
              "id": 10,
              "rationale": null,
              "role_archetype": null,
              "slug": "devops-engineer",
              "source": "db"
            },
            {
              "display_name": "Ionic Developer",
              "id": 434,
              "rationale": null,
              "role_archetype": null,
              "slug": "ionic-developer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "Maven",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "Apache Spark",
          "alias_type": "CANONICAL",
          "id": 2004,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "apache spark 3",
          "alias_type": "VERSION",
          "id": 2006,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "spark",
          "alias_type": "VERSION",
          "id": 2510,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "spark 3",
          "alias_type": "VERSION",
          "id": 2007,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "spark 3.x",
          "alias_type": "VERSION",
          "id": 2009,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "spark3",
          "alias_type": "VERSION",
          "id": 2008,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 5,
        "display_name": "Apache Spark",
        "id": 1350,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "FRAMEWORK",
        "slug": "apache-spark",
        "sub_category_id": 1021,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "ETL and ELT Tooling",
            "id": 24,
            "rationale": "Packaged tools for extracting, loading, and transforming data across systems. This dimension covers connector-based ingestion, transformation frameworks, and managed integration products.",
            "slug": "etl-and-elt-tooling",
            "source": "db"
          },
          "input_skill": "Apache Spark",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Data Engineer",
              "id": 2,
              "rationale": null,
              "role_archetype": null,
              "slug": "data-engineer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "Apache Spark",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [],
      "canonical": null,
      "dimensions": [],
      "input_skill": "Unix Shell Scripting",
      "matched_via": null,
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": {
        "derived": {
          "category": "Programming Languages",
          "skill_nature": "LANGUAGE",
          "sub_category": "general",
          "typical_lifespan": "MULTI_YEAR",
          "version_strategy": "UNVERSIONED",
          "volatility": "MEDIUM"
        },
        "enrichment": null,
        "keep_log": [],
        "locked_dimensions": [],
        "merge_log": [],
        "placed": null,
        "relationships": null,
        "skill_id": "unix-shell-scripting",
        "split_log": [],
        "typed": null,
        "warnings": []
      },
      "source_tag": "llm",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [],
      "canonical": null,
      "dimensions": [],
      "input_skill": "Unix",
      "matched_via": null,
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": {
        "derived": {
          "category": "Operating Systems",
          "skill_nature": "PLATFORM",
          "sub_category": "general",
          "typical_lifespan": "EVERGREEN",
          "version_strategy": "UNVERSIONED",
          "volatility": "STABLE"
        },
        "enrichment": null,
        "keep_log": [],
        "locked_dimensions": [],
        "merge_log": [],
        "placed": null,
        "relationships": null,
        "skill_id": "unix",
        "split_log": [],
        "typed": null,
        "warnings": []
      },
      "source_tag": "llm",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [],
      "canonical": null,
      "dimensions": [],
      "input_skill": "HDFS",
      "matched_via": null,
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": {
        "derived": {
          "category": "Data Engineering Tools",
          "skill_nature": "TOOL",
          "sub_category": "general",
          "typical_lifespan": "MULTI_YEAR",
          "version_strategy": "UNVERSIONED",
          "volatility": "MEDIUM"
        },
        "enrichment": null,
        "keep_log": [],
        "locked_dimensions": [],
        "merge_log": [],
        "placed": null,
        "relationships": null,
        "skill_id": "hdfs",
        "split_log": [],
        "typed": null,
        "warnings": []
      },
      "source_tag": "llm",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "Oracle Database",
          "alias_type": "CANONICAL",
          "id": 2512,
          "is_primary": true,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 3,
        "display_name": "Oracle Database",
        "id": 1566,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "TOOL",
        "slug": "oracle-database",
        "sub_category_id": 29,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "React Frontend Development",
            "id": 96,
            "rationale": "Building interactive web user interfaces with React.js, including component composition, state management, hooks, and rendering patterns. React.js belongs here because it is a core library for client-side UI development in modern web applications.",
            "slug": "d_init_01",
            "source": "db"
          },
          "input_skill": "Oracle SQL",
          "llm_role": null,
          "roles_from_db": []
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Relational Database Design",
            "id": 4,
            "rationale": "Modeling and operating relational persistence for backend services. Includes schema design, normalization, indexing, transactions, and query tuning for operational data stores.",
            "slug": "relational-database-design",
            "source": "db"
          },
          "input_skill": "Oracle SQL",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": ".NET Backend Developer",
              "id": 83,
              "rationale": null,
              "role_archetype": "Engineering",
              "slug": "dotnet-backend-developer",
              "source": "db"
            },
            {
              "display_name": "Backend Developer",
              "id": 1,
              "rationale": null,
              "role_archetype": "A Backend Engineer designs, builds, and maintains the server-side logic and data handling that power applications and services. They focus on implementing reliable business functionality, integrating with other systems, and ensuring the backend is scalable, maintainable, and observable.",
              "slug": "backend-engineer",
              "source": "db"
            },
            {
              "display_name": "Kotlin Backend Developer",
              "id": 84,
              "rationale": null,
              "role_archetype": "Engineering",
              "slug": "kotlin-server-backend-developer",
              "source": "db"
            },
            {
              "display_name": "Node.js Backend Developer",
              "id": 82,
              "rationale": null,
              "role_archetype": "Engineering",
              "slug": "node-backend-developer",
              "source": "db"
            },
            {
              "display_name": "Python Backend Developer",
              "id": 80,
              "rationale": null,
              "role_archetype": "Engineering",
              "slug": "python-backend-developer",
              "source": "db"
            },
            {
              "display_name": "Ruby Backend Developer",
              "id": 85,
              "rationale": null,
              "role_archetype": "Engineering",
              "slug": "ruby-backend-developer",
              "source": "db"
            },
            {
              "display_name": "Scala Backend Developer",
              "id": 87,
              "rationale": null,
              "role_archetype": "Engineering",
              "slug": "scala-backend-developer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "Oracle SQL",
      "matched_via": "embedding_alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [],
      "canonical": null,
      "dimensions": [],
      "input_skill": "Hive SQL",
      "matched_via": null,
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": {
        "derived": {
          "category": "Query Languages",
          "skill_nature": "LANGUAGE",
          "sub_category": "general",
          "typical_lifespan": "MULTI_YEAR",
          "version_strategy": "UNVERSIONED",
          "volatility": "MEDIUM"
        },
        "enrichment": null,
        "keep_log": [],
        "locked_dimensions": [],
        "merge_log": [],
        "placed": null,
        "relationships": null,
        "skill_id": "hive-sql",
        "split_log": [],
        "typed": null,
        "warnings": []
      },
      "source_tag": "llm",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [],
      "canonical": null,
      "dimensions": [],
      "input_skill": "Spark SQL",
      "matched_via": null,
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": {
        "derived": {
          "category": "Query Languages",
          "skill_nature": "LANGUAGE",
          "sub_category": "general",
          "typical_lifespan": "MULTI_YEAR",
          "version_strategy": "UNVERSIONED",
          "volatility": "MEDIUM"
        },
        "enrichment": null,
        "keep_log": [],
        "locked_dimensions": [],
        "merge_log": [],
        "placed": null,
        "relationships": null,
        "skill_id": "spark-sql",
        "split_log": [],
        "typed": null,
        "warnings": []
      },
      "source_tag": "llm",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [],
      "canonical": null,
      "dimensions": [],
      "input_skill": "Impala",
      "matched_via": null,
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": {
        "derived": {
          "category": "Data Engineering Tools",
          "skill_nature": "TOOL",
          "sub_category": "general",
          "typical_lifespan": "MULTI_YEAR",
          "version_strategy": "UNVERSIONED",
          "volatility": "MEDIUM"
        },
        "enrichment": null,
        "keep_log": [],
        "locked_dimensions": [],
        "merge_log": [],
        "placed": null,
        "relationships": null,
        "skill_id": "impala",
        "split_log": [],
        "typed": null,
        "warnings": []
      },
      "source_tag": "llm",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "HBase",
          "alias_type": "CANONICAL",
          "id": 2011,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 3,
        "display_name": "HBase",
        "id": 1352,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "TOOL",
        "slug": "hbase",
        "sub_category_id": 31,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Cloud Storage and Data Services",
            "id": 144,
            "rationale": "Cloud-native storage and managed data services used to place workloads, choose durability tiers, and define platform boundaries. This is a coherent cluster because architects evaluate storage fit, access patterns, and managed service tradeoffs.",
            "slug": "cloud-storage-and-data-services",
            "source": "db"
          },
          "input_skill": "HBase",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Cloud Architect",
              "id": 9,
              "rationale": null,
              "role_archetype": null,
              "slug": "cloud-architect",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "HBase",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "CI/CD",
          "alias_type": "CANONICAL",
          "id": 1826,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 8,
        "display_name": "CI/CD",
        "id": 1190,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "METHODOLOGY",
        "slug": "ci-cd",
        "sub_category_id": 900,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "CI/CD Pipeline Platforms",
            "id": 150,
            "rationale": "Systems used to define, run, and maintain automated build and deployment workflows. This cluster is coherent because the role owns delivery automation end to end, including pipeline reliability and promotion logic.",
            "slug": "ci-cd-pipeline-platforms",
            "source": "db"
          },
          "input_skill": "CI/CD",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "DevOps Engineer",
              "id": 10,
              "rationale": null,
              "role_archetype": null,
              "slug": "devops-engineer",
              "source": "db"
            }
          ]
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "CI/CD for Machine Learning",
            "id": 56,
            "rationale": "Tools and platforms for automating ML model integration, testing, and deployment pipelines.",
            "slug": "ci-cd-for-machine-learning",
            "source": "db"
          },
          "input_skill": "CI/CD",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "ML Engineer",
              "id": 3,
              "rationale": null,
              "role_archetype": null,
              "slug": "ml-engineer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "CI/CD",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "Hive",
          "alias_type": "CANONICAL",
          "id": 4198,
          "is_primary": true,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 3,
        "display_name": "Hive",
        "id": 2754,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "TOOL",
        "slug": "hive",
        "sub_category_id": 2242,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Local Persistence and Offline Behavior",
            "id": 85,
            "rationale": "On-device storage used for caching, offline support, and durable client state. This cluster is coherent because iOS apps often need to preserve user progress and data when connectivity is limited.",
            "slug": "local-persistence-and-offline-behavior",
            "source": "db"
          },
          "input_skill": "Hive",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Android Developer",
              "id": 4,
              "rationale": null,
              "role_archetype": null,
              "slug": "android-engineer",
              "source": "db"
            },
            {
              "display_name": "Flutter Developer",
              "id": 74,
              "rationale": null,
              "role_archetype": "Engineering",
              "slug": "flutter-developer",
              "source": "db"
            },
            {
              "display_name": "Hybrid Mobile Developer",
              "id": 11,
              "rationale": null,
              "role_archetype": null,
              "slug": "hybrid-mobile-developer",
              "source": "db"
            },
            {
              "display_name": "Native Mobile Developer",
              "id": 75,
              "rationale": null,
              "role_archetype": "Engineering",
              "slug": "native-mobile-developer",
              "source": "db"
            },
            {
              "display_name": "React Native Developer",
              "id": 73,
              "rationale": null,
              "role_archetype": "Engineering",
              "slug": "react-native-developer",
              "source": "db"
            },
            {
              "display_name": "iOS Developer",
              "id": 6,
              "rationale": null,
              "role_archetype": null,
              "slug": "ios-engineer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "Hive",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    }
  ],
  "unmatched_skills": [
    "Unix Shell Scripting",
    "Unix",
    "HDFS",
    "Hive SQL",
    "Spark SQL",
    "Impala"
  ]
}

{
  "chosen_role": {
    "display_name": "Data Engineer",
    "id": 2,
    "rationale": "Exact alias hit on data-engineer (1.0) \u2014 no other alias at this confidence; skill_top devops-engineer 0.15 does not contradict",
    "role_archetype": null,
    "slug": "data-engineer",
    "source": "db"
  },
  "chosen_role_resolution": "in_db",
  "final_input_skills": [
    {
      "skill": "Scala",
      "tag": "in_db"
    },
    {
      "skill": "Maven",
      "tag": "in_db"
    },
    {
      "skill": "Apache Spark",
      "tag": "in_db"
    },
    {
      "skill": "Unix Shell Scripting",
      "tag": "new"
    },
    {
      "skill": "Unix",
      "tag": "new"
    },
    {
      "skill": "HDFS",
      "tag": "new"
    },
    {
      "skill": "Oracle SQL",
      "tag": "in_db"
    },
    {
      "skill": "Hive SQL",
      "tag": "new"
    },
    {
      "skill": "Spark SQL",
      "tag": "new"
    },
    {
      "skill": "Impala",
      "tag": "new"
    },
    {
      "skill": "HBase",
      "tag": "in_db"
    },
    {
      "skill": "CI/CD",
      "tag": "in_db"
    },
    {
      "skill": "Hive",
      "tag": "in_db"
    }
  ],
  "llm_cost_api1_usd": null,
  "llm_cost_api2_usd": null,
  "llm_cost_api3_usd": null,
  "llm_cost_total_usd": null,
  "persistence": {
    "items": [
      {
        "chosen_role_id": 2,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Programming Languages for Data Work",
          "id": 21,
          "rationale": "Languages used to implement data pipelines, transformations, and operational glue. This is the primary coding surface for building ingestion, enrichment, and automation logic in data engineering.",
          "slug": "programming-languages-for-data-work",
          "source": "db"
        },
        "dimension_id": 21,
        "input_skill": "Scala",
        "llm_role": null,
        "matched_chosen_role": true,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension saved",
        "role_dimension_saved": true,
        "roles_from_db": [
          {
            "display_name": "Data Engineer",
            "id": 2,
            "rationale": null,
            "role_archetype": null,
            "slug": "data-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 102,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 2,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Programming Languages for ML Systems",
          "id": 39,
          "rationale": "Languages used to build training code, inference services, evaluation jobs, and ML glue code. This is the primary implementation surface for ML engineers across experimentation and productionization.",
          "slug": "programming-languages-for-ml-systems",
          "source": "db"
        },
        "dimension_id": 39,
        "input_skill": "Scala",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "ML Engineer",
            "id": 3,
            "rationale": null,
            "role_archetype": null,
            "slug": "ml-engineer",
            "source": "db"
          },
          {
            "display_name": "MLOps Engineer",
            "id": 16,
            "rationale": null,
            "role_archetype": null,
            "slug": "ml-ops-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 102,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 2,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Build and Dependency Management",
          "id": 286,
          "rationale": "Project build, packaging, and dependency resolution skills used to compile and assemble Java services. This cluster matters because backend delivery depends on reproducible builds and controlled library versions.",
          "slug": "build-and-dependency-management",
          "source": "db"
        },
        "dimension_id": 286,
        "input_skill": "Maven",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Java Backend Developer",
            "id": 79,
            "rationale": null,
            "role_archetype": "Engineering",
            "slug": "java-backend-developer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 815,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 2,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Build and Packaging Tooling",
          "id": 149,
          "rationale": "Tooling used to compile, package, and prepare Ionic apps for development and release. This cluster is coherent because Ionic developers often manage web assets, native wrappers, and environment-specific build outputs.",
          "slug": "build-and-packaging-tooling",
          "source": "db"
        },
        "dimension_id": 149,
        "input_skill": "Maven",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "DevOps Engineer",
            "id": 10,
            "rationale": null,
            "role_archetype": null,
            "slug": "devops-engineer",
            "source": "db"
          },
          {
            "display_name": "Ionic Developer",
            "id": 434,
            "rationale": null,
            "role_archetype": null,
            "slug": "ionic-developer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 815,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 2,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "ETL and ELT Tooling",
          "id": 24,
          "rationale": "Packaged tools for extracting, loading, and transforming data across systems. This dimension covers connector-based ingestion, transformation frameworks, and managed integration products.",
          "slug": "etl-and-elt-tooling",
          "source": "db"
        },
        "dimension_id": 24,
        "input_skill": "Apache Spark",
        "llm_role": null,
        "matched_chosen_role": true,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension saved",
        "role_dimension_saved": true,
        "roles_from_db": [
          {
            "display_name": "Data Engineer",
            "id": 2,
            "rationale": null,
            "role_archetype": null,
            "slug": "data-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 1350,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 2,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "React Frontend Development",
          "id": 96,
          "rationale": "Building interactive web user interfaces with React.js, including component composition, state management, hooks, and rendering patterns. React.js belongs here because it is a core library for client-side UI development in modern web applications.",
          "slug": "d_init_01",
          "source": "db"
        },
        "dimension_id": 96,
        "input_skill": "Oracle SQL",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Skipped \u2014 no persistable v3 meta for new skill",
        "role_dimension_saved": false,
        "roles_from_db": [],
        "skill_dimension_saved": false,
        "skill_id": null,
        "skill_tag": "new",
        "skipped_reason": "skill_not_in_db_v3_proposed"
      },
      {
        "chosen_role_id": 2,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Relational Database Design",
          "id": 4,
          "rationale": "Modeling and operating relational persistence for backend services. Includes schema design, normalization, indexing, transactions, and query tuning for operational data stores.",
          "slug": "relational-database-design",
          "source": "db"
        },
        "dimension_id": 4,
        "input_skill": "Oracle SQL",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Skipped \u2014 no persistable v3 meta for new skill",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": ".NET Backend Developer",
            "id": 83,
            "rationale": null,
            "role_archetype": "Engineering",
            "slug": "dotnet-backend-developer",
            "source": "db"
          },
          {
            "display_name": "Backend Developer",
            "id": 1,
            "rationale": null,
            "role_archetype": "A Backend Engineer designs, builds, and maintains the server-side logic and data handling that power applications and services. They focus on implementing reliable business functionality, integrating with other systems, and ensuring the backend is scalable, maintainable, and observable.",
            "slug": "backend-engineer",
            "source": "db"
          },
          {
            "display_name": "Kotlin Backend Developer",
            "id": 84,
            "rationale": null,
            "role_archetype": "Engineering",
            "slug": "kotlin-server-backend-developer",
            "source": "db"
          },
          {
            "display_name": "Node.js Backend Developer",
            "id": 82,
            "rationale": null,
            "role_archetype": "Engineering",
            "slug": "node-backend-developer",
            "source": "db"
          },
          {
            "display_name": "Python Backend Developer",
            "id": 80,
            "rationale": null,
            "role_archetype": "Engineering",
            "slug": "python-backend-developer",
            "source": "db"
          },
          {
            "display_name": "Ruby Backend Developer",
            "id": 85,
            "rationale": null,
            "role_archetype": "Engineering",
            "slug": "ruby-backend-developer",
            "source": "db"
          },
          {
            "display_name": "Scala Backend Developer",
            "id": 87,
            "rationale": null,
            "role_archetype": "Engineering",
            "slug": "scala-backend-developer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": false,
        "skill_id": null,
        "skill_tag": "new",
        "skipped_reason": "skill_not_in_db_v3_proposed"
      },
      {
        "chosen_role_id": 2,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Cloud Storage and Data Services",
          "id": 144,
          "rationale": "Cloud-native storage and managed data services used to place workloads, choose durability tiers, and define platform boundaries. This is a coherent cluster because architects evaluate storage fit, access patterns, and managed service tradeoffs.",
          "slug": "cloud-storage-and-data-services",
          "source": "db"
        },
        "dimension_id": 144,
        "input_skill": "HBase",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Cloud Architect",
            "id": 9,
            "rationale": null,
            "role_archetype": null,
            "slug": "cloud-architect",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 1352,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 2,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "CI/CD Pipeline Platforms",
          "id": 150,
          "rationale": "Systems used to define, run, and maintain automated build and deployment workflows. This cluster is coherent because the role owns delivery automation end to end, including pipeline reliability and promotion logic.",
          "slug": "ci-cd-pipeline-platforms",
          "source": "db"
        },
        "dimension_id": 150,
        "input_skill": "CI/CD",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "DevOps Engineer",
            "id": 10,
            "rationale": null,
            "role_archetype": null,
            "slug": "devops-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 1190,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 2,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "CI/CD for Machine Learning",
          "id": 56,
          "rationale": "Tools and platforms for automating ML model integration, testing, and deployment pipelines.",
          "slug": "ci-cd-for-machine-learning",
          "source": "db"
        },
        "dimension_id": 56,
        "input_skill": "CI/CD",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "ML Engineer",
            "id": 3,
            "rationale": null,
            "role_archetype": null,
            "slug": "ml-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 1190,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 2,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Local Persistence and Offline Behavior",
          "id": 85,
          "rationale": "On-device storage used for caching, offline support, and durable client state. This cluster is coherent because iOS apps often need to preserve user progress and data when connectivity is limited.",
          "slug": "local-persistence-and-offline-behavior",
          "source": "db"
        },
        "dimension_id": 85,
        "input_skill": "Hive",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Android Developer",
            "id": 4,
            "rationale": null,
            "role_archetype": null,
            "slug": "android-engineer",
            "source": "db"
          },
          {
            "display_name": "Flutter Developer",
            "id": 74,
            "rationale": null,
            "role_archetype": "Engineering",
            "slug": "flutter-developer",
            "source": "db"
          },
          {
            "display_name": "Hybrid Mobile Developer",
            "id": 11,
            "rationale": null,
            "role_archetype": null,
            "slug": "hybrid-mobile-developer",
            "source": "db"
          },
          {
            "display_name": "Native Mobile Developer",
            "id": 75,
            "rationale": null,
            "role_archetype": "Engineering",
            "slug": "native-mobile-developer",
            "source": "db"
          },
          {
            "display_name": "React Native Developer",
            "id": 73,
            "rationale": null,
            "role_archetype": "Engineering",
            "slug": "react-native-developer",
            "source": "db"
          },
          {
            "display_name": "iOS Developer",
            "id": 6,
            "rationale": null,
            "role_archetype": null,
            "slug": "ios-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 2754,
        "skill_tag": "in_db",
        "skipped_reason": null
      }
    ],
    "new_skills_created": 0,
    "role_dimension_saved": 0,
    "skill_dimension_saved": 0,
    "skipped": 2
  },
  "planner_output": null,
  "run_id": "9bd37876-38fa-4481-9ba5-d79d3dc251b3"
}