← Back to history

Pipeline run

ac2115f3-bb2c-4372-9c29-23edaa5ba3fc

Pipeline LLM cost (USD)
API 1: $0.0030 API 2: $0.0002 API 3: $0.0000 Total: $0.0032

Client output enrichment

v2 Skill cluster · Nature of work · AI index · Tech stack maturity · Evidence · KRA description
SPARSE JD role baseline loaded sources · ai_index: role_baseline · nature_of_work: jd · tech_stack_maturity: jd
Nature of work · Data pipeline development
Build and own complex ETL/data pipelines and data layers, translating business needs into a data engineering roadmap and delivering large-scale data projects with cross-functional teams.
""Design and build data pipelines to schedule & orchestrate a variety of tasks such as extract, cleanse, transform, enrich & load data as per the business needs""
Tech stack maturity
Mainstream Modern
AI index (0 = no AI use, 5 = totally AI-dependent · v2.1)
1.20 / 5
· Title match
· Has AI skill
· AI skill (primary)
· AI skill (secondary)
· On AI team
· Builds AI products
vocab breakdown (legacy)
Assistants (×1):
Frameworks (×2):
Models / concepts (×3):
Evidence — skills matched in JD (4)
Data Pipelines ETL Data Engineering Large-scale Systems
Skill cluster (1 dimension groups, role-scoped)
Cross-cutting / unaligned
Data Pipelines ETL Data Engineering Large-scale Systems
Show KRA description ↓
Collaborate with engineering/product/analyst teams across tech sites to collectively accomplish OKRs to take Uber forward Enrich data layers to effectively deal with the next generation of products which are a result of Uber's big bold bets Design and build data pipelines to schedule & orchestrate a variety of tasks such as extract, cleanse, transform, enrich & load data as per the business needs We are seeking a strong and passionate data engineer with experience in large-scale system implementation, with a focus on complex data pipelines. The candidate should be able to design and drive large projects from inception to production. The right person will work with cross-functional businesses', and technology partners to gather requirements and translate them into a data engineering roadmap. Must be a great communicator, standout teammate, and a technology powerhouse.

Signals

Skill
Alias data-engineer
1.00
KRA data-engineer
0.58

Post-classification

Centroidupdated · n=422
Alias collision log
New-role queue
New skills captured4
New KRA captured

Captured for admin review

Data Pipelines primary Data Engineer pending
ETL primary Data Engineer pending
Data Engineering primary Data Engineer pending
Large-scale Systems Data Engineer pending
Status: completed Created: 2026-05-27T16:20:33.885703Z Updated: 2026-05-27T16:21:25.465136Z API 3 duration: 2280 ms
Flow Current 3-step pipeline

1 POST /skills/extract-from-jd

2 POST /skills/extract-details

3 POST /skills/final-role-output

Role Chosen role & resolution

Data Engineer

CASE A

slug: data-engineer · id: 2 · source: db

Exact alias hit on data-engineer (1.0) — no other alias at this confidence; skill_top absent does not contradict

Resolution: in_db — role exists in library; skill↔dim and role↔dim links saved when applicable.

0
New skills
0
Skill↔dim saved
0
Role↔dim saved
0
Skipped

Job description

About Uber

Uber is a technology company that is changing the way the world thinks about transportation. We are building technology people use every day. Whether it's heading home from work, getting a meal delivered from a favorite restaurant, or a way to earn extra income, Uber is becoming part of the fabric of daily life.

We're making cities safer, smarter, and more connected. And we're doing it at a global scale-energizing the local economy and bringing opportunity to millions of people around the world. We ignite opportunity by setting the world in motion!

Uber's positive impact is tangible in the communities we operate in, and that drives us to keep moving forward.

About The Team

The Data Engineering team at Hyderabad collaborates with Engineering, Product, and Analytics teams across tech sites to collectively accomplish OKRs to take Uber forward. We constantly enrich our data layer to optimally deal with the next generation of products which are a result of our big bold bets.

We design and build data pipelines to schedule & orchestrate a variety of tasks such as extract, cleanse, transform, enrich, and load data as per the business needs. We serve data insights at depth to various teams at Uber-like business analytics, data analytics, data science, and other business partners to make strategic decisions, train DS models, perform health checks, etc.

What We're Looking For

We are seeking a strong and passionate data engineer with experience in large-scale system implementation, with a focus on complex data pipelines. The candidate should be able to design and drive large projects from inception to production. The right person will work with cross-functional businesses', and technology partners to gather requirements and translate them into a data engineering roadmap. Must be a great communicator, standout teammate, and a technology powerhouse.

What You'll Do
Collaborate with engineering/product/analyst teams across tech sites to collectively accomplish OKRs to take Uber forwardEnrich data layers to effectively deal with the next generation of products which are a result of Uber's big bold betsDesign and build data pipelines to schedule & orchestrate a variety of tasks such as extract, cleanse, transform, enrich & load data as per the business needs
What You'll Need
Strong SQL skillsStrong in Data Warehousing and Data Modelling conceptsHands-on experience in Hadoop tech stack:HDFS, Hive, Oozie, Airflow, MapReduce, Spark.Programming languages - Python, Java, Scala, etc.Experience in building ETL Data PipelinesPerformance Troubleshooting and Tuning

Skills from this JD

Each row merges API 1 extraction, API 2 library match / v3 orchestration (dimensions + locked dims), and API 3 persistence tags.

Data Pipelines Primary New / orchestrated API 3: new canonical path (new) New / unmatched skill (orchestrated in API 2)

Skill enrichment (orchestrator / LLM)

No Stage 7 enrichment blob on this skill (orchestrator skipped enrichment).

Derived legacy fields
Category
Data Engineering Tools
Sub-category
general
Skill nature
CONCEPT
Volatility
MEDIUM
Typical lifespan
MULTI_YEAR
Version strategy
UNVERSIONED
ETL Primary New / orchestrated API 3: new canonical path (new) New / unmatched skill (orchestrated in API 2)

Skill enrichment (orchestrator / LLM)

No Stage 7 enrichment blob on this skill (orchestrator skipped enrichment).

Derived legacy fields
Category
Data Engineering Tools
Sub-category
general
Skill nature
CONCEPT
Volatility
MEDIUM
Typical lifespan
MULTI_YEAR
Version strategy
UNVERSIONED
Data Engineering Primary New / orchestrated API 3: new canonical path (new) New / unmatched skill (orchestrated in API 2)

Skill enrichment (orchestrator / LLM)

No Stage 7 enrichment blob on this skill (orchestrator skipped enrichment).

Derived legacy fields
Category
Data Engineering Tools
Sub-category
general
Skill nature
CONCEPT
Volatility
STABLE
Typical lifespan
EVERGREEN
Version strategy
UNVERSIONED
Large-scale Systems Secondary New / orchestrated API 3: new canonical path (new) New / unmatched skill (orchestrated in API 2)

Skill enrichment (orchestrator / LLM)

No Stage 7 enrichment blob on this skill (orchestrator skipped enrichment).

Derived legacy fields
Category
Concepts
Sub-category
general
Skill nature
CONCEPT
Volatility
MEDIUM
Typical lifespan
MULTI_YEAR
Version strategy
UNVERSIONED

Library artifacts (this run)

Kind Detail DB id
canonical_skill_proposed Data Pipelines | type=Data Engineering Tools subtype=general nature=CONCEPT lifespan=MULTI_YEAR
canonical_skill_proposed ETL | type=Data Engineering Tools subtype=general nature=CONCEPT lifespan=MULTI_YEAR
canonical_skill_proposed Data Engineering | type=Data Engineering Tools subtype=general nature=CONCEPT lifespan=EVERGREEN
canonical_skill_proposed Large-scale Systems | type=Concepts subtype=general nature=CONCEPT lifespan=MULTI_YEAR
nano JD Parser — gpt-4.1-nano click to toggle
RoleData Engineer
CompanyUber
DomainIT Services & Consulting
Location Hyderabad, India
JD type pass
Show raw JSON
{
  "JD_type": "pass",
  "about_company": {
    "source_marker": {
      "first_5_words": "Uber is a technology company",
      "last_5_words": "drives us to keep moving forward."
    },
    "text": "Uber is a technology company that is changing the way the world thinks about transportation. We are building technology people use every day. Whether it\u0027s heading home from work, getting a meal delivered from a favorite restaurant, or a way to earn extra income, Uber is becoming part of the fabric of daily life.\n\nWe\u0027re making cities safer, smarter, and more connected. And we\u0027re doing it at a global scale-energizing the local economy and bringing opportunity to millions of people around the world. We ignite opportunity by setting the world in motion!\n\nUber\u0027s positive impact is tangible in the communities we operate in, and that drives us to keep moving forward.",
    "word_count": 104
  },
  "certifications": [],
  "company_name": "Uber",
  "ctc": null,
  "domain": {
    "primary": {
      "aliases": [
        "Tech Services",
        "Technology"
      ],
      "domain": "IT Services \u0026 Consulting"
    },
    "secondary": null
  },
  "education": [],
  "experience": {
    "max": null,
    "min": null,
    "raw": null
  },
  "job_locations": [
    {
      "aliases": [
        "Hyderabad, TG"
      ],
      "city": "Hyderabad",
      "country": "India",
      "state": "Telangana",
      "work_mode": null
    }
  ],
  "role": "Data Engineer",
  "role_aliases": [
    "Data Engineer",
    "Data Pipeline Engineer",
    "ETL Engineer"
  ],
  "role_archetype": "Data",
  "roles_and_responsibilities": [
    {
      "bullet_count": 0,
      "heading": "What You\u0027ll Do",
      "heading_was_present": true,
      "source_marker": {
        "first_5_words": "Collaborate with engineering/product/analyst teams",
        "last_5_words": "as per the business needs"
      },
      "text": "Collaborate with engineering/product/analyst teams across tech sites to collectively accomplish OKRs to take Uber forward\nEnrich data layers to effectively deal with the next generation of products which are a result of Uber\u0027s big bold bets\nDesign and build data pipelines to schedule \u0026 orchestrate a variety of tasks such as extract, cleanse, transform, enrich \u0026 load data as per the business needs",
      "word_count": 50
    },
    {
      "bullet_count": 0,
      "heading": "What We\u0027re Looking For",
      "heading_was_present": true,
      "source_marker": {
        "first_5_words": "We are seeking a strong",
        "last_5_words": "and a technology powerhouse."
      },
      "text": "We are seeking a strong and passionate data engineer with experience in large-scale system implementation, with a focus on complex data pipelines. The candidate should be able to design and drive large projects from inception to production. The right person will work with cross-functional businesses\u0027, and technology partners to gather requirements and translate them into a data engineering roadmap. Must be a great communicator, standout teammate, and a technology powerhouse.",
      "word_count": 63
    }
  ],
  "urls": []
}
API 1 — extract-from-jd click to toggle
{
  "final_skills": [
    {
      "is_primary": true,
      "skill_name": "Data Pipelines"
    },
    {
      "is_primary": true,
      "skill_name": "ETL"
    },
    {
      "is_primary": true,
      "skill_name": "Data Engineering"
    },
    {
      "is_primary": false,
      "skill_name": "Large-scale Systems"
    }
  ],
  "jd_role": {
    "display_name": "Data Engineer",
    "rationale": null,
    "role_aliases": [
      "Data Engineer",
      "Data Pipeline Engineer",
      "ETL Engineer"
    ],
    "role_archetype": "Data",
    "slug": ""
  },
  "nano_parsed": {
    "JD_type": "pass",
    "about_company": {
      "source_marker": {
        "first_5_words": "Uber is a technology company",
        "last_5_words": "drives us to keep moving forward."
      },
      "text": "Uber is a technology company that is changing the way the world thinks about transportation. We are building technology people use every day. Whether it\u0027s heading home from work, getting a meal delivered from a favorite restaurant, or a way to earn extra income, Uber is becoming part of the fabric of daily life.\n\nWe\u0027re making cities safer, smarter, and more connected. And we\u0027re doing it at a global scale-energizing the local economy and bringing opportunity to millions of people around the world. We ignite opportunity by setting the world in motion!\n\nUber\u0027s positive impact is tangible in the communities we operate in, and that drives us to keep moving forward.",
      "word_count": 104
    },
    "certifications": [],
    "company_name": "Uber",
    "ctc": null,
    "domain": {
      "primary": {
        "aliases": [
          "Tech Services",
          "Technology"
        ],
        "domain": "IT Services \u0026 Consulting"
      },
      "secondary": null
    },
    "education": [],
    "experience": {
      "max": null,
      "min": null,
      "raw": null
    },
    "job_locations": [
      {
        "aliases": [
          "Hyderabad, TG"
        ],
        "city": "Hyderabad",
        "country": "India",
        "state": "Telangana",
        "work_mode": null
      }
    ],
    "role": "Data Engineer",
    "role_aliases": [
      "Data Engineer",
      "Data Pipeline Engineer",
      "ETL Engineer"
    ],
    "role_archetype": "Data",
    "roles_and_responsibilities": [
      {
        "bullet_count": 0,
        "heading": "What You\u0027ll Do",
        "heading_was_present": true,
        "source_marker": {
          "first_5_words": "Collaborate with engineering/product/analyst teams",
          "last_5_words": "as per the business needs"
        },
        "text": "Collaborate with engineering/product/analyst teams across tech sites to collectively accomplish OKRs to take Uber forward\nEnrich data layers to effectively deal with the next generation of products which are a result of Uber\u0027s big bold bets\nDesign and build data pipelines to schedule \u0026 orchestrate a variety of tasks such as extract, cleanse, transform, enrich \u0026 load data as per the business needs",
        "word_count": 50
      },
      {
        "bullet_count": 0,
        "heading": "What We\u0027re Looking For",
        "heading_was_present": true,
        "source_marker": {
          "first_5_words": "We are seeking a strong",
          "last_5_words": "and a technology powerhouse."
        },
        "text": "We are seeking a strong and passionate data engineer with experience in large-scale system implementation, with a focus on complex data pipelines. The candidate should be able to design and drive large projects from inception to production. The right person will work with cross-functional businesses\u0027, and technology partners to gather requirements and translate them into a data engineering roadmap. Must be a great communicator, standout teammate, and a technology powerhouse.",
        "word_count": 63
      }
    ],
    "urls": []
  },
  "rejected": false,
  "rejection_reason": null,
  "run_id": "ac2115f3-bb2c-4372-9c29-23edaa5ba3fc",
  "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": "Works with data analysts, data scientists, and business stakeholders to define data models, ingestion schedules, and data delivery requirements.",
            "sentence": "Design and build data pipelines to schedule \u0026 orchestrate a variety of tasks such as extract, cleanse, transform, enrich \u0026 load data as per the business needs",
            "similarity": 0.6498
          },
          {
            "kra_text": "Works with data analysts, data scientists, and business stakeholders to define data models, ingestion schedules, and data delivery requirements.",
            "sentence": "The right person will work with cross-functional businesses\u0027, and technology partners to gather requirements and translate them into a data engineering roadmap.",
            "similarity": 0.5977
          },
          {
            "kra_text": "Works with data analysts, data scientists, and business stakeholders to define data models, ingestion schedules, and data delivery requirements.",
            "sentence": "We are seeking a strong and passionate data engineer with experience in large-scale system implementation, with a focus on complex data pipelines.",
            "similarity": 0.5069
          }
        ],
        "matched_count": null,
        "matched_skills": null,
        "role_id": 2,
        "score": 0.5848,
        "slug": "data-engineer",
        "total_count": null
      },
      {
        "display_name": "Flutter Developer",
        "kra_matches": [
          {
            "kra_text": "collaborate with design, product, and backend teams",
            "sentence": "Collaborate with engineering/product/analyst teams across tech sites to collectively accomplish OKRs to take Uber forward",
            "similarity": 0.5705
          },
          {
            "kra_text": "collaborate with design, product, and backend teams",
            "sentence": "The right person will work with cross-functional businesses\u0027, and technology partners to gather requirements and translate them into a data engineering roadmap.",
            "similarity": 0.4651
          },
          {
            "kra_text": "collaborate with design, product, and backend teams",
            "sentence": "The candidate should be able to design and drive large projects from inception to production.",
            "similarity": 0.4152
          }
        ],
        "matched_count": null,
        "matched_skills": null,
        "role_id": 74,
        "score": 0.4836,
        "slug": "flutter-developer",
        "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": "Design and build data pipelines to schedule \u0026 orchestrate a variety of tasks such as extract, cleanse, transform, enrich \u0026 load data as per the business needs",
            "similarity": 0.5329
          },
          {
            "kra_text": "Translates product requirements into machine learning system specifications including feature definitions, model architecture choices, and success metric definitions.",
            "sentence": "The right person will work with cross-functional businesses\u0027, and technology partners to gather requirements and translate them into a data engineering roadmap.",
            "similarity": 0.4814
          },
          {
            "kra_text": "Prepares, cleans, and transforms training datasets, manages feature stores, and builds feature engineering pipelines for model training.",
            "sentence": "We are seeking a strong and passionate data engineer with experience in large-scale system implementation, with a focus on complex data pipelines.",
            "similarity": 0.3974
          }
        ],
        "matched_count": null,
        "matched_skills": null,
        "role_id": 3,
        "score": 0.4705,
        "slug": "ml-engineer",
        "total_count": null
      },
      {
        "display_name": "Fullstack Developer",
        "kra_matches": [
          {
            "kra_text": "Works closely with product managers and UX designers to translate requirements and wireframes into working software features through iterative development.",
            "sentence": "The right person will work with cross-functional businesses\u0027, and technology partners to gather requirements and translate them into a data engineering roadmap.",
            "similarity": 0.4867
          },
          {
            "kra_text": "Designs and queries relational databases like PostgreSQL and document stores like MongoDB, writing migrations, indexes, and optimized queries.",
            "sentence": "Design and build data pipelines to schedule \u0026 orchestrate a variety of tasks such as extract, cleanse, transform, enrich \u0026 load data as per the business needs",
            "similarity": 0.4456
          },
          {
            "kra_text": "Works closely with product managers and UX designers to translate requirements and wireframes into working software features through iterative development.",
            "sentence": "Collaborate with engineering/product/analyst teams across tech sites to collectively accomplish OKRs to take Uber forward",
            "similarity": 0.4367
          }
        ],
        "matched_count": null,
        "matched_skills": null,
        "role_id": 15,
        "score": 0.4563,
        "slug": "full-stack-engineer",
        "total_count": null
      },
      {
        "display_name": "Cloud Architect",
        "kra_matches": [
          {
            "kra_text": "Conducts architecture reviews, approves technical design documents, and guides engineering teams through cloud migration and modernization projects.",
            "sentence": "The right person will work with cross-functional businesses\u0027, and technology partners to gather requirements and translate them into a data engineering roadmap.",
            "similarity": 0.4566
          },
          {
            "kra_text": "Designs backup policies, cross-region replication, and disaster recovery runbooks to meet defined RTO and RPO targets for critical workloads.",
            "sentence": "Design and build data pipelines to schedule \u0026 orchestrate a variety of tasks such as extract, cleanse, transform, enrich \u0026 load data as per the business needs",
            "similarity": 0.4359
          },
          {
            "kra_text": "Conducts architecture reviews, approves technical design documents, and guides engineering teams through cloud migration and modernization projects.",
            "sentence": "The candidate should be able to design and drive large projects from inception to production.",
            "similarity": 0.4354
          }
        ],
        "matched_count": null,
        "matched_skills": null,
        "role_id": 9,
        "score": 0.4426,
        "slug": "cloud-architect",
        "total_count": null
      }
    ],
    "skill_match_roles": []
  },
  "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 absent does not contradict",
    "sub_role": null
  },
  "stage5_updates": {
    "centroid_n_after": 422,
    "centroid_updated": true,
    "collision_log_id": null,
    "new_kra_attached": null,
    "new_skills_attached": [
      {
        "is_primary": true,
        "queue_id": 19564,
        "role_display_name": "Data Engineer",
        "role_slug": "data-engineer",
        "skill_name": "Data Pipelines",
        "status": "pending"
      },
      {
        "is_primary": true,
        "queue_id": 19565,
        "role_display_name": "Data Engineer",
        "role_slug": "data-engineer",
        "skill_name": "ETL",
        "status": "pending"
      },
      {
        "is_primary": true,
        "queue_id": 19566,
        "role_display_name": "Data Engineer",
        "role_slug": "data-engineer",
        "skill_name": "Data Engineering",
        "status": "pending"
      },
      {
        "is_primary": false,
        "queue_id": 19567,
        "role_display_name": "Data Engineer",
        "role_slug": "data-engineer",
        "skill_name": "Large-scale Systems",
        "status": "pending"
      }
    ],
    "queue_entry_id": null,
    "v3_pipeline_triggered": false,
    "v3_role_slug": null,
    "v3_run_id": null
  }
}
API 2 — extract-details
{
  "alias_matches": [],
  "candidate_roles": [],
  "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 absent does not contradict",
    "role_archetype": null,
    "slug": "data-engineer",
    "source": "db"
  },
  "dimensions": [],
  "input_final_skills": [
    "Data Pipelines",
    "ETL",
    "Data Engineering",
    "Large-scale Systems"
  ],
  "input_llm_skills": [
    "Data Pipelines",
    "ETL",
    "Data Engineering",
    "Large-scale Systems"
  ],
  "new_aliases_persisted": 0,
  "run_id": "ac2115f3-bb2c-4372-9c29-23edaa5ba3fc",
  "skills_detail": [
    {
      "aliases_in_db": [],
      "canonical": null,
      "dimensions": [],
      "input_skill": "Data Pipelines",
      "matched_via": null,
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": {
        "derived": {
          "category": "Data Engineering Tools",
          "skill_nature": "CONCEPT",
          "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": "data-pipelines",
        "split_log": [],
        "typed": null,
        "warnings": []
      },
      "source_tag": "llm",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [],
      "canonical": null,
      "dimensions": [],
      "input_skill": "ETL",
      "matched_via": null,
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": {
        "derived": {
          "category": "Data Engineering Tools",
          "skill_nature": "CONCEPT",
          "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": "etl",
        "split_log": [],
        "typed": null,
        "warnings": []
      },
      "source_tag": "llm",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [],
      "canonical": null,
      "dimensions": [],
      "input_skill": "Data Engineering",
      "matched_via": null,
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": {
        "derived": {
          "category": "Data Engineering Tools",
          "skill_nature": "CONCEPT",
          "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": "data-engineering",
        "split_log": [],
        "typed": null,
        "warnings": []
      },
      "source_tag": "llm",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [],
      "canonical": null,
      "dimensions": [],
      "input_skill": "Large-scale Systems",
      "matched_via": null,
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": {
        "derived": {
          "category": "Concepts",
          "skill_nature": "CONCEPT",
          "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": "large-scale-systems",
        "split_log": [],
        "typed": null,
        "warnings": []
      },
      "source_tag": "llm",
      "was_in_llm_skills": true
    }
  ],
  "unmatched_skills": [
    "Data Pipelines",
    "ETL",
    "Data Engineering",
    "Large-scale Systems"
  ]
}
API 3 — final-role-output
{
  "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 absent does not contradict",
    "role_archetype": null,
    "slug": "data-engineer",
    "source": "db"
  },
  "chosen_role_resolution": "in_db",
  "final_input_skills": [
    {
      "skill": "Data Pipelines",
      "tag": "new"
    },
    {
      "skill": "ETL",
      "tag": "new"
    },
    {
      "skill": "Data Engineering",
      "tag": "new"
    },
    {
      "skill": "Large-scale Systems",
      "tag": "new"
    }
  ],
  "llm_cost_api1_usd": null,
  "llm_cost_api2_usd": null,
  "llm_cost_api3_usd": null,
  "llm_cost_total_usd": null,
  "persistence": {
    "items": [],
    "new_skills_created": 0,
    "role_dimension_saved": 0,
    "skill_dimension_saved": 0,
    "skipped": 0
  },
  "planner_output": null,
  "run_id": "ac2115f3-bb2c-4372-9c29-23edaa5ba3fc"
}