Senior Platform Data Engineer

Job Summary

The Senior Platform Data Engineer owns roadmap, priorities, platform standards, and architecture reviews; provides formal input on performance reviews. This position makes clinical data ready for AI at scale: owning the shared data products, retrieval infrastructure, and platform administration that the entire AI portfolio depends on. Owns real‑time data feeds, reusable clinical data models and feature pipelines, RAG retrieval infrastructure, and Databricks platform administration.

• Streams data from Epic SDE, ADT feeds, lab results, and other clinical sources into Databricks for downstream model consumption.
• Curates shared clinical feature tables (patient demographics, labs, vitals, diagnoses, utilization history, imaging metadata) in Databricks/Unity Catalog that multiple AI programs consume for model training, validation, and monitoring.
• Owns RAG infrastructure, the shared retrieval‑augmented generation platform that agentic and generative AI programs use to ground LLM outputs in organizational knowledge.
• Designs and operates document ingestion pipelines: normalizing clinical documents, policies, guidelines, and unstructured data sources into formats ready for embedding and retrieval.
• Implements and optimizes chunking strategies tailored to healthcare content (e.g., preserving clinical note structure, section‑aware chunking for guidelines and protocols).
• Manages the embedding pipeline: selecting, tuning, and versioning embedding models (domain‑specific clinical models where they outperform general‑purpose).
• Administers the vector database: schema design, indexing, metadata management, access controls, and performance tuning.
• Builds and maintains retrieval pipelines: hybrid search (vector + keyword/BM25), reranking, and relevance filtering to maximize retrieval precision for downstream agents and LLM applications.
• Establishes data quality gates for RAG: automated profiling, completeness checks, and accuracy scoring before content enters the vector store.
• Monitors retrieval quality metrics (Precision@K, Recall@K, MRR) and continuously optimizes retrieval performance.
• Databricks workspace configuration and Unity Catalog governance.
• Cluster policies, compute management, and cost monitoring.
• Manges user/group management and access control.
• Administrator for Feature Store.

• Databricks (Delta Live Tables, Feature Store, PySpark, Unity Catalog)
• Epic SDE / epic-ws for real‑time clinical data extraction
• Vector databases (Pinecone, Weaviate, Qdrant, or Databricks Vector Search)
• Embedding models and pipelines (clinical domain‑specific and general‑purpose)
• SQL, pandas
• Streaming and batch ingestion patterns
• CDIS Data Warehouse (source system for batch clinical data)

• 5+ years in data engineering, with strong experience building both batch and streaming data pipelines
• Expert‑level Databricks skills:
  Delta Live Tables, PySpark, Unity Catalog, Feature Store
• Hands‑on experience with real‑time data ingestion (Kafka, Spark Structured Streaming, or comparable frameworks)
• Strong SQL and Python (pandas, PySpark) skills for data transformation and feature engineering
• Experience administering Databricks work spaces: cluster policies, compute management, access controls, cost monitoring
• Familiarity with clinical data models and healthcare data sources (EHR extracts, ADT feeds, lab results, claims data) strongly preferred
• Experience with Epic data extraction methods (SDE, FHIR, epic‑ws) a significant plus
• Understanding of data governance principles: lineage, quality monitoring, access controls

Bachelor's Degree‑Related Field of Study (Required), Master's Degree‑Related Field of Study (Preferred)

Minimum of 5 years‑Relevant experience (Required)

We are proud to be an affirmative action, equal opportunity employer and all qualified applicants will receive consideration for employment regardless to race, color, religion, sex, sexual orientation, gender identity, national origin, disability or status as a protected veteran.