Position: Senior Data Engineer – Clinical Data Harness & Synthetic Data
Location: Edina, MN or Chicago, IL
Duration: Long Term
Client: Elevance Health
Job Summary
Seeking a hands-on Senior Data Engineer with strong Databricks experience and specialized expertise in clinical data de-identification and synthetic data generation. The candidate will develop automated, scalable workflows to protect sensitive clinical data and generate realistic synthetic datasets for analytics, AI/ML development, testing, and research.
Required Skills:
Direct experience building or working with clinical data harnesses and automated clinical data de-identification.
Strong hands-on experience with Databricks, Apache Spark, PySpark, Python, and SQL.
Knowledge of HIPAA Safe Harbor (18 identifiers), Expert Determination, and applicable GDPR requirements.
Experience with de-identification techniques such as suppression, generalization, consistent date shifting, pseudonymization, tokenization, and cryptographic hashing.
Experience generating synthetic tabular or clinical data using techniques such as Bayesian networks, copulas, GANs/CTGAN, VAEs, or transformer/LLM-based models.
Familiarity with synthetic data tools such as SDV (Synthetic Data Vault), Gretel, or comparable frameworks.
Understanding of privacy and re-identification risk, data quality, statistical fidelity, and synthetic data utility.
Preferred Skills:
Healthcare data experience involving EHR, claims, laboratory data, clinical notes, HL7, or FHIR.
Experience scaling de-identification and synthetic data generation workflows on Spark/Databricks.
Experience with Unity Catalog, data governance, access controls, lineage, and auditability.
