Lead data science across a $31B revenue-cycle system, turning operational data into decisions leadership acts on.

• Built a Claude Agents-driven interactive KPI scorecard integrating 31 KPIs across a $31B revenue-cycle system.
• Engineered statistical confidence intervals for Real-Time Eligibility (RTE) optimization, giving leadership quantified confidence bounds on a $13M strategic investment decision.

Owned production ML across the largest publicly operated health plan in the U.S., from ETL to models validated in the real world.

• Shipped production PySpark ETLs with LightGBM classifiers across Hive data warehouses to predict adverse member outcomes, validated via RCT to deliver $7M in averted adverse outcomes.
• Built and operationalized an LLM-integrated medication NER system on Azure, extracting regulatory-compliance signals from unstructured notes and preventing $2M in regulatory violations.
• Designed the DHCS risk-stratification data model (RSST) to improve health-equity visibility into at-risk populations.
• Built a standardized HPI data pipeline for cross-team geospatial equity analysis and intervention targeting.

Ran the compute and research pipeline behind two published transformer models for air-pollution forecasting.

• Designed and managed a Weights & Biases-integrated GCP environment for high-compute PyTorch Lightning models, producing two air-pollution-prediction publications using state-of-the-art transformers.
• Taught graduate students algorithmic proofs and implementation in Java.