{
  "id": "role:data-engineer",
  "_kind": "Role",
  "_file": "domain/roles/roles-engineering.yaml",
  "_cluster": "domain",
  "attributes": {
    "displayName": "Data Engineer",
    "isAgentic": false,
    "automatability": 0.8,
    "description": "Designs and operates the data infrastructure — pipelines, warehouses, and\nstreaming systems — that move raw data from source systems to analytics and\nproduct consumers in a reliable, scalable, and governed way. Partners with data\nscientists, analysts, and product teams to understand data needs and model\ndatasets appropriately. Owns data quality monitoring and pipeline observability.\n",
    "seniority": "mid"
  },
  "outgoingEdges": [
    {
      "from": "role:data-engineer",
      "to": "responsibility:data-quality",
      "kind": "holds_responsibility"
    },
    {
      "from": "role:data-engineer",
      "to": "responsibility:on-call",
      "kind": "holds_responsibility"
    },
    {
      "from": "role:data-engineer",
      "to": "responsibility:documentation",
      "kind": "holds_responsibility"
    },
    {
      "from": "role:data-engineer",
      "to": "responsibility:performance-optimization",
      "kind": "holds_responsibility"
    },
    {
      "from": "role:data-engineer",
      "to": "domain:data-engineering",
      "kind": "requires_skill",
      "attributes": {
        "level": "expert"
      }
    },
    {
      "from": "role:data-engineer",
      "to": "specialization:data-engineering-analytics",
      "kind": "requires_skill",
      "attributes": {
        "level": "expert"
      }
    },
    {
      "from": "role:data-engineer",
      "to": "domain:databases",
      "kind": "requires_skill",
      "attributes": {
        "level": "expert"
      }
    },
    {
      "from": "role:data-engineer",
      "to": "domain:cloud-infra",
      "kind": "requires_skill",
      "attributes": {
        "level": "intermediate"
      }
    },
    {
      "from": "role:data-engineer",
      "to": "responsibility:data-quality",
      "kind": "holds_responsibility"
    },
    {
      "from": "role:data-engineer",
      "to": "responsibility:data-quality-monitoring",
      "kind": "holds_responsibility"
    },
    {
      "from": "role:data-engineer",
      "to": "responsibility:documentation",
      "kind": "holds_responsibility"
    },
    {
      "from": "role:data-engineer",
      "to": "skill-area:etl-pipelines",
      "kind": "requires_expertise",
      "attributes": {}
    },
    {
      "from": "role:data-engineer",
      "to": "skill-area:data-warehouse-modeling",
      "kind": "requires_expertise",
      "attributes": {}
    },
    {
      "from": "role:data-engineer",
      "to": "skill-area:dbt-modeling",
      "kind": "requires_expertise",
      "attributes": {}
    },
    {
      "from": "role:data-engineer",
      "to": "skill-area:data-quality",
      "kind": "requires_expertise",
      "attributes": {}
    },
    {
      "from": "role:data-engineer",
      "to": "skill-area:data-lineage",
      "kind": "requires_expertise",
      "attributes": {}
    },
    {
      "from": "role:data-engineer",
      "to": "skill-area:spark-jobs",
      "kind": "requires_expertise",
      "attributes": {}
    },
    {
      "from": "role:data-engineer",
      "to": "skill-area:batch-vs-stream-tradeoffs",
      "kind": "requires_expertise",
      "attributes": {}
    }
  ],
  "incomingEdges": [
    {
      "from": "stack-profile:data-lakehouse",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "stack-profile:stream-processing",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "stack-profile:feature-store-mlops",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "stack-profile:edge-ai-iot",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "stack-profile:search-discovery",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "stack-profile:document-processing-pipeline",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "stack-profile:geospatial-analytics",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "stack-profile:batch-processing",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "stack-profile:insurance-claims-processing",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "stack-profile:adtech-real-time-bidding",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "stack-profile:knowledge-graph-platform",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "stack-profile:synthetic-data-generation",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "stack-profile:data-warehouse-bi",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "stack-profile:time-series-analytics",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "stack-profile:data-quality-governance",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "stack-profile:enterprise-search-platform",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "stack-profile:master-data-management",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "stack-profile:research-data-platform",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "stack-profile:social-network-backend",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "stack-profile:julia-data-service",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "stack-profile:cqrs-read-model",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "stack-profile:data-pipeline-orchestration",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "stack-profile:etl-reverse-etl",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "stack-profile:real-time-analytics-stack",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "stack-profile:fastapi-postgres",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "stack-profile:rag-stack",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "stack-profile:data-lake-stack",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "stack-profile:event-driven-stack",
      "to": "role:data-engineer",
      "kind": "used_by_role"
    },
    {
      "from": "tool:databricks",
      "to": "role:data-engineer",
      "kind": "supports_work",
      "attributes": {
        "confidence": "high",
        "evidence": "Ora surfaced Databricks as a top match for data engineering orchestration and warehouse workflows."
      }
    },
    {
      "from": "tool:snowflake",
      "to": "role:data-engineer",
      "kind": "supports_work",
      "attributes": {
        "confidence": "high",
        "evidence": "Ora surfaced Snowflake for warehouse and data orchestration workflows."
      }
    },
    {
      "from": "tool:dbt-labs",
      "to": "role:data-engineer",
      "kind": "supports_work",
      "attributes": {
        "confidence": "high",
        "evidence": "dbt transformations and lineage support data engineering workflows."
      }
    },
    {
      "from": "workflow:data-pipeline-deployment",
      "to": "role:data-engineer",
      "kind": "involves_role"
    },
    {
      "from": "workflow:ml-model-lifecycle",
      "to": "role:data-engineer",
      "kind": "involves_role"
    },
    {
      "from": "workflow:data-quality-monitoring",
      "to": "role:data-engineer",
      "kind": "involves_role"
    },
    {
      "from": "workflow:data-governance-review",
      "to": "role:data-engineer",
      "kind": "involves_role"
    },
    {
      "from": "workflow:schema-migration",
      "to": "role:data-engineer",
      "kind": "involves_role"
    },
    {
      "from": "workflow:data-backfill-procedure",
      "to": "role:data-engineer",
      "kind": "involves_role"
    },
    {
      "from": "tool-server:mcp-dbt-candidate",
      "to": "role:data-engineer",
      "kind": "supports_work",
      "attributes": {
        "confidence": "medium",
        "evidence": "dbt metadata and run status would support data engineering and analytics-engineering workflows."
      }
    },
    {
      "from": "lib-agent:code-migration-modernization--data-architect-agent",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 0.7
      }
    },
    {
      "from": "lib-agent:code-migration-modernization--data-integrity-validator",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-agent:code-migration-modernization--database-migration-orchestrator",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-agent:data-engineering-analytics--data-governance-steward",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-agent:data-engineering-analytics--data-orchestration-engineer",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-agent:data-engineering-analytics--data-quality-engineer",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-agent:data-engineering-analytics--data-warehouse-architect",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-agent:data-engineering-analytics--dbt-project-engineer",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 0.7
      }
    },
    {
      "from": "lib-agent:data-engineering-analytics--migration-specialist",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-agent:data-engineering-analytics--ml-feature-engineer",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-agent:data-engineering-analytics--streaming-pipeline-engineer",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-agent:data-science-ml--data-engineer",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-agent:data-science-ml--feature-store-engineer",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 0.7
      }
    },
    {
      "from": "lib-agent:knowledge-management--kg-specialist",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 0.7
      }
    },
    {
      "from": "lib-agent:travel--python-etl-engineer",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-agent:travel--sql-query-composer",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 0.5
      }
    },
    {
      "from": "lib-agent:travel--sqlite-schema-architect",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-agent:physics--research-data-manager",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 0.7
      }
    },
    {
      "from": "lib-agent:healthcare--clinical-informatics-specialist",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-agent:software-architecture--data-architect",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 0.7
      }
    },
    {
      "from": "lib-process:software-architecture--data-architecture-design",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 0.7
      }
    },
    {
      "from": "lib-skill:code-migration-modernization--data-migration-validator",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-skill:code-migration-modernization--etl-pipeline-builder",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-skill:code-migration-modernization--query-translator",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-skill:code-migration-modernization--schema-comparator",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-skill:common-utilities--json-data-wrangling",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 0.7
      }
    },
    {
      "from": "lib-skill:cryptography-blockchain--subgraph-indexing",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 0.7
      }
    },
    {
      "from": "lib-skill:data-engineering-analytics--airflow-dag-analyzer",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-skill:data-engineering-analytics--apache-spark-optimizer",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-skill:data-engineering-analytics--batch-vs-stream-tradeoffs",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-skill:data-engineering-analytics--cdc-pattern-implementer",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-skill:data-engineering-analytics--cost-optimizer",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-skill:data-engineering-analytics--data-catalog-enricher",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-skill:data-engineering-analytics--data-lineage-mapper",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-skill:data-engineering-analytics--data-quality-profiler",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-skill:data-engineering-analytics--dbt-project-analyzer",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 0.7
      }
    },
    {
      "from": "lib-skill:data-engineering-analytics--dimensional-model-validator",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 0.7
      }
    },
    {
      "from": "lib-skill:data-engineering-analytics--etl-testing",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-skill:data-engineering-analytics--feature-engineering-optimizer",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-skill:data-engineering-analytics--great-expectations-generator",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-skill:data-engineering-analytics--incremental-model-strategy-selector",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 0.7
      }
    },
    {
      "from": "lib-skill:data-engineering-analytics--kafka-topic-designer",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-skill:data-engineering-analytics--obt-design-optimizer",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 0.7
      }
    },
    {
      "from": "lib-skill:data-engineering-analytics--scd-implementation-generator",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 0.7
      }
    },
    {
      "from": "lib-skill:data-engineering-analytics--schema-evolution-manager",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-skill:data-engineering-analytics--spark-jobs",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-skill:data-engineering-analytics--sql-query-optimizer",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-skill:data-engineering-analytics--stream-processing-windowing-designer",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-skill:data-science-ml--feast-feature-store",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 0.7
      }
    },
    {
      "from": "lib-skill:knowledge-management--autocomplete-engine",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 0.7
      }
    },
    {
      "from": "lib-skill:healthcare--health-data-integration",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-skill:humanities--metadata-standards-implementation",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-skill:humanities--tei-text-encoding",
      "to": "role:data-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 0.7
      }
    },
    {
      "from": "org-unit:data-team",
      "to": "role:data-engineer",
      "kind": "has_member",
      "attributes": {}
    },
    {
      "from": "org-unit:data-platform-team",
      "to": "role:data-engineer",
      "kind": "has_member",
      "attributes": {}
    },
    {
      "from": "org-unit:business-intelligence-team",
      "to": "role:data-engineer",
      "kind": "has_member",
      "attributes": {}
    },
    {
      "from": "responsibility:data-quality-monitoring",
      "to": "role:data-engineer",
      "kind": "held_by",
      "attributes": {}
    },
    {
      "from": "responsibility:data-pipeline-reliability",
      "to": "role:data-engineer",
      "kind": "held_by",
      "attributes": {}
    },
    {
      "from": "workflow:synthetic-data-generation-pipeline",
      "to": "role:data-engineer",
      "kind": "involves_role",
      "attributes": {}
    },
    {
      "from": "workflow:data-quality-scorecard-review",
      "to": "role:data-engineer",
      "kind": "involves_role",
      "attributes": {}
    },
    {
      "from": "workflow:analytics-instrumentation-audit",
      "to": "role:data-engineer",
      "kind": "involves_role",
      "attributes": {}
    },
    {
      "from": "workflow:self-serve-analytics-enablement",
      "to": "role:data-engineer",
      "kind": "involves_role",
      "attributes": {}
    },
    {
      "from": "workflow:enterprise-data-platform-health-check",
      "to": "role:data-engineer",
      "kind": "involves_role",
      "attributes": {}
    },
    {
      "from": "workflow:data-quality-investigation",
      "to": "role:data-engineer",
      "kind": "involves_role",
      "attributes": {}
    },
    {
      "from": "workflow:model-training-pipeline",
      "to": "role:data-engineer",
      "kind": "involves_role",
      "attributes": {}
    },
    {
      "from": "workflow:data-quality-check",
      "to": "role:data-engineer",
      "kind": "involves_role",
      "attributes": {}
    },
    {
      "from": "workflow:data-migration",
      "to": "role:data-engineer",
      "kind": "involves_role",
      "attributes": {}
    },
    {
      "from": "workflow:alternative-data-evaluation",
      "to": "role:data-engineer",
      "kind": "involves_role",
      "attributes": {}
    },
    {
      "from": "workflow:market-data-feed-validation",
      "to": "role:data-engineer",
      "kind": "involves_role",
      "attributes": {}
    }
  ]
}