Data Engineer - AI, Agents, & Context - Revenue Cycle (Associate)
Core
Building and maintaining core AI/context data capabilities including unstructured ingestion, embeddings, retrieval, and semantic layers for a healthcare-wide AI platform.
Role type
Associate Data Engineer (AI/Context Platform)
Builds
Healthcare-wide AI data and context platform (semantic layers, retrieval services, agent-ready interfaces)
Domain
Healthcare technology / AI infrastructure
Deliverable
production ML models | infrastructure
Required skills
SQL, Python, Snowflake, cloud data pipelines, unstructured data processing, search/retrieval concepts
Preferred skills
vector search and embeddings, LLM applications (RAG, agent tool interfaces), knowledge graphs, data governance, dbt, Iceberg
Technologies
Snowflake, vector search tools (pgvector/Pinecone/Weaviate/OpenSearch/Elastic), dbt, Iceberg
Responsibilities
Implement end-to-end pipelines (ingestion, parsing, chunking, enrichment, embeddings, vector indexing, retrieval); Build and maintain patterns for incremental refresh, backfills, re-embeddings, deduplication, and lineage; Implement semantic layers (metrics/entities) that power BI and agent reasoning; Apply security-by-design patterns (RBAC/ABAC, PII redaction, retention controls, audit logging); Support reliability and performance (monitoring, alerting, runbooks, incident response); Contribute to cost and latency optimization across Snowflake and vector infrastructure
Seniority
Associate, hands-on IC
