Data Engineer - AI, Agents, & Context - Clinical (Sr. Associate)
Core
Building a healthcare-wide AI data and context platform to turn structured and unstructured information into trusted, reusable building blocks for product innovation and agent reasoning.
Role type
Senior Associate Data Engineer (AI/Context Platform)
Builds
Production-grade AI data products including ingestion pipelines, embeddings, vector indexing, retrieval services, and semantic layers for healthcare clients.
Domain
Healthcare technology, AI infrastructure, unstructured data processing, and semantic modeling.
Deliverable
production ML models | product features
Required skills
SQL, Python, cloud data pipeline design, unstructured data processing, search/retrieval concepts, production engineering habits.
Preferred skills
Vector search and embeddings (pgvector/Pinecone/Weaviate/OpenSearch/Elastic), RAG and agent tool interfaces, knowledge graphs/semantic modeling, regulated environment data governance.
Technologies
Cloud data warehouses/lakehouses, vector databases, embedding models, retrieval frameworks.
Responsibilities
Implement end-to-end pipelines for ingestion, parsing, chunking, enrichment, embeddings, vector indexing, and retrieval; Build and maintain patterns for incremental refresh, backfills, re-embeddings, and deduplication; Implement semantic layers and data contracts for AI inputs; Support reliability, performance, cost, and latency optimization; Apply security-by-design patterns including RBAC/ABAC, PII redaction, and audit logging.
Seniority
Senior Associate, hands-on IC contributor.
