Pipeline run

{
  "final_skills": [
    {
      "is_primary": true,
      "skill_name": "HDFS"
    },
    {
      "is_primary": true,
      "skill_name": "YARN"
    },
    {
      "is_primary": true,
      "skill_name": "MR2"
    },
    {
      "is_primary": true,
      "skill_name": "Hive"
    },
    {
      "is_primary": true,
      "skill_name": "Tez"
    },
    {
      "is_primary": true,
      "skill_name": "Ranger"
    },
    {
      "is_primary": true,
      "skill_name": "ZooKeeper"
    },
    {
      "is_primary": true,
      "skill_name": "Presto"
    },
    {
      "is_primary": true,
      "skill_name": "Airflow"
    },
    {
      "is_primary": true,
      "skill_name": "Spark"
    },
    {
      "is_primary": true,
      "skill_name": "Kubernetes"
    },
    {
      "is_primary": true,
      "skill_name": "NiFi"
    }
  ],
  "jd_role": {
    "display_name": "Big Data Engineer",
    "rationale": null,
    "role_aliases": [
      "Big Data Developer",
      "Open Source Engineer"
    ],
    "role_archetype": "Engineering",
    "slug": ""
  },
  "nano_parsed": {
    "JD_type": "pass",
    "about_company": null,
    "certifications": [],
    "company_name": "Apptad Technologies Pvt Ltd",
    "ctc": {
      "currency": null,
      "max": null,
      "min": null,
      "period": null,
      "raw": "Negotiable"
    },
    "domain": {
      "primary": {
        "aliases": [],
        "domain": "Other"
      },
      "secondary": null
    },
    "education": [],
    "experience": {
      "max": null,
      "min": null,
      "raw": null
    },
    "job_locations": [
      {
        "aliases": [],
        "city": null,
        "country": null,
        "state": null,
        "work_mode": "remote"
      }
    ],
    "role": "Big Data Engineer",
    "role_aliases": [
      "Big Data Developer",
      "Open Source Engineer"
    ],
    "role_archetype": "Engineering",
    "roles_and_responsibilities": [
      {
        "bullet_count": 10,
        "heading": "Role",
        "heading_was_present": true,
        "source_marker": {
          "first_5_words": "Open Source Engineer/Developer with experience",
          "last_5_words": "big data stacks internal)"
        },
        "text": "Open Source Engineer/Developer with experience using the following Hadoop components:\n\u00b7        HDFS (HDP 3.15 and HDP 2.6.5)\n\u00b7        Yarn\n\u00b7        MR2\n\u00b7        Hive(Tez)\n\u00b7        Ranger\n\u00b7        Zookeeper\n\u00b7        Presto\n\u00b7        Airflow\n\u00b7        Spark 3.x on k8s\n\u00b7        Nifi\nAdditional Comments: We are looking for candidates who understand the open-source stacks internals. Good understanding of the big data stacks internals.\n(Not looking for Candidates who have build applications over Hive/Hadoop/Spark but who have a good understanding of big data stacks internal)",
        "word_count": 104
      }
    ],
    "urls": []
  },
  "rejected": false,
  "rejection_reason": null,
  "run_id": "d5481561-9410-4334-9f14-41d520d9541f",
  "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": "(Not looking for Candidates who have build applications over Hive/Hadoop/Spark but who have a good understanding of big data stacks internal)",
            "similarity": 0.5244
          },
          {
            "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": "Open Source Engineer/Developer with experience using the following Hadoop components:",
            "similarity": 0.5097
          },
          {
            "kra_text": "Works with data analysts, data scientists, and business stakeholders to define data models, ingestion schedules, and data delivery requirements.",
            "sentence": "Additional Comments: We are looking for candidates who understand the open-source stacks internals.",
            "similarity": 0.2963
          }
        ],
        "matched_count": null,
        "matched_skills": null,
        "role_id": 2,
        "score": 0.4434,
        "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": "(Not looking for Candidates who have build applications over Hive/Hadoop/Spark but who have a good understanding of big data stacks internal)",
            "similarity": 0.4029
          },
          {
            "kra_text": "Debugs full-stack issues that span frontend rendering, API behavior, database queries, and infrastructure configuration to identify root causes.",
            "sentence": "Additional Comments: We are looking for candidates who understand the open-source stacks internals.",
            "similarity": 0.3669
          },
          {
            "kra_text": "Designs and queries relational databases like PostgreSQL and document stores like MongoDB, writing migrations, indexes, and optimized queries.",
            "sentence": "Open Source Engineer/Developer with experience using the following Hadoop components:",
            "similarity": 0.3643
          }
        ],
        "matched_count": null,
        "matched_skills": null,
        "role_id": 15,
        "score": 0.378,
        "slug": "full-stack-engineer",
        "total_count": null
      },
      {
        "display_name": "DevOps Engineer",
        "kra_matches": [
          {
            "kra_text": "Collaborates with development teams to improve build processes, reduce deployment friction, containerize applications, and adopt DevOps best practices.",
            "sentence": "Open Source Engineer/Developer with experience using the following Hadoop components:",
            "similarity": 0.3647
          },
          {
            "kra_text": "Collaborates with development teams to improve build processes, reduce deployment friction, containerize applications, and adopt DevOps best practices.",
            "sentence": "Additional Comments: We are looking for candidates who understand the open-source stacks internals.",
            "similarity": 0.3378
          },
          {
            "kra_text": "Builds and maintains CI/CD pipelines using Jenkins, GitHub Actions, GitLab CI, or CircleCI to automate build, test, security scanning, and deployment workflows.",
            "sentence": "(Not looking for Candidates who have build applications over Hive/Hadoop/Spark but who have a good understanding of big data stacks internal)",
            "similarity": 0.3209
          }
        ],
        "matched_count": null,
        "matched_skills": null,
        "role_id": 10,
        "score": 0.3412,
        "slug": "devops-engineer",
        "total_count": null
      },
      {
        "display_name": "Cloud Architect",
        "kra_matches": [
          {
            "kra_text": "Evaluates cloud-native managed services, serverless compute, PaaS databases, and CDN solutions for workload fit and total cost of ownership.",
            "sentence": "(Not looking for Candidates who have build applications over Hive/Hadoop/Spark but who have a good understanding of big data stacks internal)",
            "similarity": 0.3627
          },
          {
            "kra_text": "Conducts architecture reviews, approves technical design documents, and guides engineering teams through cloud migration and modernization projects.",
            "sentence": "Additional Comments: We are looking for candidates who understand the open-source stacks internals.",
            "similarity": 0.3306
          },
          {
            "kra_text": "Designs multi-region and multi-availability-zone cloud infrastructure architectures for high availability, fault tolerance, and horizontal scalability.",
            "sentence": "Open Source Engineer/Developer with experience using the following Hadoop components:",
            "similarity": 0.3269
          }
        ],
        "matched_count": null,
        "matched_skills": null,
        "role_id": 9,
        "score": 0.34,
        "slug": "cloud-architect",
        "total_count": null
      },
      {
        "display_name": "Backend Developer",
        "kra_matches": [
          {
            "kra_text": "Identifies and resolves backend performance bottlenecks through query optimization, indexing strategies, connection pooling, and distributed caching with Redis.",
            "sentence": "(Not looking for Candidates who have build applications over Hive/Hadoop/Spark but who have a good understanding of big data stacks internal)",
            "similarity": 0.3434
          },
          {
            "kra_text": "Identifies and resolves backend performance bottlenecks through query optimization, indexing strategies, connection pooling, and distributed caching with Redis.",
            "sentence": "Additional Comments: We are looking for candidates who understand the open-source stacks internals.",
            "similarity": 0.3403
          },
          {
            "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": "Open Source Engineer/Developer with experience using the following Hadoop components:",
            "similarity": 0.3345
          }
        ],
        "matched_count": null,
        "matched_skills": null,
        "role_id": 1,
        "score": 0.3394,
        "slug": "backend-engineer",
        "total_count": null
      }
    ],
    "skill_match_roles": [
      {
        "display_name": "MLOps Engineer",
        "kra_matches": null,
        "matched_count": 2,
        "matched_skills": [
          "Airflow",
          "Kubernetes"
        ],
        "role_id": 16,
        "score": 0.1667,
        "slug": "ml-ops-engineer",
        "total_count": 12
      },
      {
        "display_name": "ML Engineer",
        "kra_matches": null,
        "matched_count": 2,
        "matched_skills": [
          "Airflow",
          "Kubernetes"
        ],
        "role_id": 3,
        "score": 0.1667,
        "slug": "ml-engineer",
        "total_count": 12
      },
      {
        "display_name": "Android Developer",
        "kra_matches": null,
        "matched_count": 1,
        "matched_skills": [
          "Hive"
        ],
        "role_id": 4,
        "score": 0.0833,
        "slug": "android-engineer",
        "total_count": 12
      },
      {
        "display_name": "Cloud Architect",
        "kra_matches": null,
        "matched_count": 1,
        "matched_skills": [
          "Kubernetes"
        ],
        "role_id": 9,
        "score": 0.0833,
        "slug": "cloud-architect",
        "total_count": 12
      },
      {
        "display_name": "iOS Developer",
        "kra_matches": null,
        "matched_count": 1,
        "matched_skills": [
          "Hive"
        ],
        "role_id": 6,
        "score": 0.0833,
        "slug": "ios-engineer",
        "total_count": 12
      }
    ]
  },
  "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 ml-ops-engineer 0.17 does not contradict",
    "sub_role": null
  },
  "stage5_updates": {
    "centroid_n_after": 424,
    "centroid_updated": true,
    "collision_log_id": null,
    "new_kra_attached": null,
    "new_skills_attached": [
      {
        "is_primary": true,
        "queue_id": 19637,
        "role_display_name": "Data Engineer",
        "role_slug": "data-engineer",
        "skill_name": "HDFS",
        "status": "pending"
      },
      {
        "is_primary": true,
        "queue_id": 19638,
        "role_display_name": "Data Engineer",
        "role_slug": "data-engineer",
        "skill_name": "YARN",
        "status": "pending"
      },
      {
        "is_primary": true,
        "queue_id": 19639,
        "role_display_name": "Data Engineer",
        "role_slug": "data-engineer",
        "skill_name": "MR2",
        "status": "pending"
      },
      {
        "is_primary": true,
        "queue_id": 19640,
        "role_display_name": "Data Engineer",
        "role_slug": "data-engineer",
        "skill_name": "Tez",
        "status": "pending"
      },
      {
        "is_primary": true,
        "queue_id": 19641,
        "role_display_name": "Data Engineer",
        "role_slug": "data-engineer",
        "skill_name": "Ranger",
        "status": "pending"
      },
      {
        "is_primary": true,
        "queue_id": 19642,
        "role_display_name": "Data Engineer",
        "role_slug": "data-engineer",
        "skill_name": "ZooKeeper",
        "status": "pending"
      },
      {
        "is_primary": true,
        "queue_id": 19643,
        "role_display_name": "Data Engineer",
        "role_slug": "data-engineer",
        "skill_name": "Presto",
        "status": "pending"
      },
      {
        "is_primary": true,
        "queue_id": 19644,
        "role_display_name": "Data Engineer",
        "role_slug": "data-engineer",
        "skill_name": "NiFi",
        "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": 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"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 526,
      "existing_alias_text": "Airflow",
      "input_term": "Airflow",
      "matched_canonical": {
        "category_id": 13,
        "display_name": "Airflow",
        "id": 265,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "TOOL",
        "slug": "airflow",
        "sub_category_id": 130,
        "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": 2510,
      "existing_alias_text": "spark",
      "input_term": "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": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 1267,
      "existing_alias_text": "Kubernetes",
      "input_term": "Kubernetes",
      "matched_canonical": {
        "category_id": 9,
        "display_name": "Kubernetes",
        "id": 726,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "PLATFORM",
        "slug": "kubernetes",
        "sub_category_id": 557,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    }
  ],
  "candidate_roles": [
    {
      "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"
    },
    {
      "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": "Data Engineer",
      "id": 2,
      "rationale": null,
      "role_archetype": null,
      "slug": "data-engineer",
      "source": "db"
    },
    {
      "display_name": "Cloud Architect",
      "id": 9,
      "rationale": null,
      "role_archetype": null,
      "slug": "cloud-architect",
      "source": "db"
    },
    {
      "display_name": "DevOps Engineer",
      "id": 10,
      "rationale": null,
      "role_archetype": null,
      "slug": "devops-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 ml-ops-engineer 0.17 does not contradict",
    "role_archetype": null,
    "slug": "data-engineer",
    "source": "db"
  },
  "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"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Workflow Orchestration for ML Pipelines",
        "id": 54,
        "rationale": "Workflow engines used to coordinate training, evaluation, deployment, and retraining jobs. This cluster covers dependencies, retries, scheduling, and pipeline composition for ML lifecycle automation.",
        "slug": "workflow-orchestration-for-ml-pipelines",
        "source": "db"
      },
      "input_skill": "Airflow",
      "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": "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": "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": "Container Orchestration Platforms",
        "id": 134,
        "rationale": "Platforms that schedule and manage containerized workloads across clusters and environments. Cloud Architects need these to define workload placement standards, cluster boundaries, and platform capabilities.",
        "slug": "container-orchestration-platforms",
        "source": "db"
      },
      "input_skill": "Kubernetes",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Cloud Architect",
          "id": 9,
          "rationale": null,
          "role_archetype": null,
          "slug": "cloud-architect",
          "source": "db"
        },
        {
          "display_name": "DevOps Engineer",
          "id": 10,
          "rationale": null,
          "role_archetype": null,
          "slug": "devops-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Kubernetes for ML Workloads",
        "id": 47,
        "rationale": "Kubernetes-native components used to schedule, accelerate, and isolate ML training and serving workloads. This includes GPU enablement and ML-specific controllers rather than generic cluster administration.",
        "slug": "kubernetes-for-ml-workloads",
        "source": "db"
      },
      "input_skill": "Kubernetes",
      "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_final_skills": [
    "HDFS",
    "YARN",
    "MR2",
    "Hive",
    "Tez",
    "Ranger",
    "ZooKeeper",
    "Presto",
    "Airflow",
    "Spark",
    "Kubernetes",
    "NiFi"
  ],
  "input_llm_skills": [
    "HDFS",
    "YARN",
    "MR2",
    "Hive",
    "Tez",
    "Ranger",
    "ZooKeeper",
    "Presto",
    "Airflow",
    "Spark",
    "Kubernetes",
    "NiFi"
  ],
  "new_aliases_persisted": 0,
  "run_id": "d5481561-9410-4334-9f14-41d520d9541f",
  "skills_detail": [
    {
      "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": [],
      "canonical": null,
      "dimensions": [],
      "input_skill": "YARN",
      "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": "yarn",
        "split_log": [],
        "typed": null,
        "warnings": []
      },
      "source_tag": "llm",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [],
      "canonical": null,
      "dimensions": [],
      "input_skill": "MR2",
      "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": "mr2",
        "split_log": [],
        "typed": null,
        "warnings": []
      },
      "source_tag": "llm",
      "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
    },
    {
      "aliases_in_db": [],
      "canonical": null,
      "dimensions": [],
      "input_skill": "Tez",
      "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": "tez",
        "split_log": [],
        "typed": null,
        "warnings": []
      },
      "source_tag": "llm",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [],
      "canonical": null,
      "dimensions": [],
      "input_skill": "Ranger",
      "matched_via": null,
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": {
        "derived": {
          "category": "Security 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": "ranger",
        "split_log": [],
        "typed": null,
        "warnings": []
      },
      "source_tag": "llm",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [],
      "canonical": null,
      "dimensions": [],
      "input_skill": "ZooKeeper",
      "matched_via": null,
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": {
        "derived": {
          "category": "Message Brokers",
          "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": "zookeeper",
        "split_log": [],
        "typed": null,
        "warnings": []
      },
      "source_tag": "llm",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [],
      "canonical": null,
      "dimensions": [],
      "input_skill": "Presto",
      "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": "presto",
        "split_log": [],
        "typed": null,
        "warnings": []
      },
      "source_tag": "llm",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "Airflow",
          "alias_type": "CANONICAL",
          "id": 526,
          "is_primary": true,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "airflow 2",
          "alias_type": "VERSION",
          "id": 2477,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "airflow-2",
          "alias_type": "VERSION",
          "id": 2478,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "airflow2",
          "alias_type": "VERSION",
          "id": 2476,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "airflow2.x",
          "alias_type": "VERSION",
          "id": 2479,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "apache airflow 2",
          "alias_type": "VERSION",
          "id": 2480,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 13,
        "display_name": "Airflow",
        "id": 265,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "TOOL",
        "slug": "airflow",
        "sub_category_id": 130,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Workflow Orchestration for ML Pipelines",
            "id": 54,
            "rationale": "Workflow engines used to coordinate training, evaluation, deployment, and retraining jobs. This cluster covers dependencies, retries, scheduling, and pipeline composition for ML lifecycle automation.",
            "slug": "workflow-orchestration-for-ml-pipelines",
            "source": "db"
          },
          "input_skill": "Airflow",
          "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": "Airflow",
      "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": "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": "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": [
        {
          "alias_text": "Kubernetes",
          "alias_type": "CANONICAL",
          "id": 1267,
          "is_primary": true,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.0+",
          "alias_type": "VERSION",
          "id": 1271,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.x",
          "alias_type": "VERSION",
          "id": 1270,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes v1",
          "alias_type": "VERSION",
          "id": 1269,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "k8s",
          "alias_type": "VERSION",
          "id": 1268,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "kubernetes 1.x",
          "alias_type": "VERSION",
          "id": 1400,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "kubernetes latest",
          "alias_type": "VERSION",
          "id": 1401,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 9,
        "display_name": "Kubernetes",
        "id": 726,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "PLATFORM",
        "slug": "kubernetes",
        "sub_category_id": 557,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Container Orchestration Platforms",
            "id": 134,
            "rationale": "Platforms that schedule and manage containerized workloads across clusters and environments. Cloud Architects need these to define workload placement standards, cluster boundaries, and platform capabilities.",
            "slug": "container-orchestration-platforms",
            "source": "db"
          },
          "input_skill": "Kubernetes",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Cloud Architect",
              "id": 9,
              "rationale": null,
              "role_archetype": null,
              "slug": "cloud-architect",
              "source": "db"
            },
            {
              "display_name": "DevOps Engineer",
              "id": 10,
              "rationale": null,
              "role_archetype": null,
              "slug": "devops-engineer",
              "source": "db"
            }
          ]
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Kubernetes for ML Workloads",
            "id": 47,
            "rationale": "Kubernetes-native components used to schedule, accelerate, and isolate ML training and serving workloads. This includes GPU enablement and ML-specific controllers rather than generic cluster administration.",
            "slug": "kubernetes-for-ml-workloads",
            "source": "db"
          },
          "input_skill": "Kubernetes",
          "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": "Kubernetes",
      "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": "NiFi",
      "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": "nifi",
        "split_log": [],
        "typed": null,
        "warnings": []
      },
      "source_tag": "llm",
      "was_in_llm_skills": true
    }
  ],
  "unmatched_skills": [
    "HDFS",
    "YARN",
    "MR2",
    "Tez",
    "Ranger",
    "ZooKeeper",
    "Presto",
    "NiFi"
  ]
}

{
  "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 ml-ops-engineer 0.17 does not contradict",
    "role_archetype": null,
    "slug": "data-engineer",
    "source": "db"
  },
  "chosen_role_resolution": "in_db",
  "final_input_skills": [
    {
      "skill": "HDFS",
      "tag": "new"
    },
    {
      "skill": "YARN",
      "tag": "new"
    },
    {
      "skill": "MR2",
      "tag": "new"
    },
    {
      "skill": "Hive",
      "tag": "in_db"
    },
    {
      "skill": "Tez",
      "tag": "new"
    },
    {
      "skill": "Ranger",
      "tag": "new"
    },
    {
      "skill": "ZooKeeper",
      "tag": "new"
    },
    {
      "skill": "Presto",
      "tag": "new"
    },
    {
      "skill": "Airflow",
      "tag": "in_db"
    },
    {
      "skill": "Spark",
      "tag": "in_db"
    },
    {
      "skill": "Kubernetes",
      "tag": "in_db"
    },
    {
      "skill": "NiFi",
      "tag": "new"
    }
  ],
  "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": "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
      },
      {
        "chosen_role_id": 2,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Workflow Orchestration for ML Pipelines",
          "id": 54,
          "rationale": "Workflow engines used to coordinate training, evaluation, deployment, and retraining jobs. This cluster covers dependencies, retries, scheduling, and pipeline composition for ML lifecycle automation.",
          "slug": "workflow-orchestration-for-ml-pipelines",
          "source": "db"
        },
        "dimension_id": 54,
        "input_skill": "Airflow",
        "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": 265,
        "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": "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": "Container Orchestration Platforms",
          "id": 134,
          "rationale": "Platforms that schedule and manage containerized workloads across clusters and environments. Cloud Architects need these to define workload placement standards, cluster boundaries, and platform capabilities.",
          "slug": "container-orchestration-platforms",
          "source": "db"
        },
        "dimension_id": 134,
        "input_skill": "Kubernetes",
        "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"
          },
          {
            "display_name": "DevOps Engineer",
            "id": 10,
            "rationale": null,
            "role_archetype": null,
            "slug": "devops-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 726,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 2,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Kubernetes for ML Workloads",
          "id": 47,
          "rationale": "Kubernetes-native components used to schedule, accelerate, and isolate ML training and serving workloads. This includes GPU enablement and ML-specific controllers rather than generic cluster administration.",
          "slug": "kubernetes-for-ml-workloads",
          "source": "db"
        },
        "dimension_id": 47,
        "input_skill": "Kubernetes",
        "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": 726,
        "skill_tag": "in_db",
        "skipped_reason": null
      }
    ],
    "new_skills_created": 0,
    "role_dimension_saved": 0,
    "skill_dimension_saved": 0,
    "skipped": 0
  },
  "planner_output": null,
  "run_id": "d5481561-9410-4334-9f14-41d520d9541f"
}