Senior Platform Data Engineer

Geisinger

Pennsylvania, United States
Hybrid
5+ years data engineering experience
Expert databricks delta live tables pyspark
Real-time streaming data ingestion kafka spark
This role owns the roadmap and architecture for shared clinical data products that enable AI at scale within the organization

Job Summary

  • This role owns the roadmap and architecture for shared clinical data products that enable AI at scale within the organization.
  • The engineer will design and operate document ingestion pipelines to normalize unstructured healthcare content for retrieval-augmented generation applications.
  • Geisinger offers comprehensive healthcare benefits including vision, dental, and domestic partners starting on day one.

Matching Summary

This role owns the roadmap and architecture for shared clinical data products that enable AI at scale within the organization.

Skills & Requirements

Must-have

  • 5+ years data engineering experience
  • Expert Databricks Delta Live Tables PySpark
  • Real-time streaming data ingestion Kafka Spark
  • Vector database administration Pinecone Weaviate Qdrant
  • Clinical data models EHR extracts ADT feeds

Nice-to-have

  • Epic SDE FHIR epic-ws extraction methods
  • Domain-specific clinical embedding models
  • Hybrid search reranking optimization
  • Feature Store management expertise
  • Healthcare data governance principles

Key Requirements

  • Bachelor's degree in related field required
  • Master's degree preferred
  • Minimum 5 years relevant experience
  • US work authorization required

Work Rights

Not specified

Tailored Resume

Cover Letter