The Sr. ML Engineer will work directly with our Data Science Director to develop, refine, and productionize machine learning models that score healthcare claims against liability signals from legal, P&C, and other data sources. This role requires comfort working with structured healthcare and insurance data in a HIPAA-compliant environment.
Key Responsibilities:
- Develop and iterate on classification and scoring models (e.g., XGBoost, gradient boosting, ensemble methods) that identify subrogation recovery opportunities from health plan claims data
- Engineer features from the Gold layer and Feature Store, including injury code signals, entity match confidence, and P&C/legal filing attributes
- Collaborate with Data Engineers to ensure Feature Store pipelines deliver clean, timely feature sets for both training and inference
- Conduct model evaluation, validation, and performance benchmarking against current identification baselines
- Explore signal sources from Path B (P&C clearinghouse) and Path C (Bloomberg Law) as inputs to Paragon scoring logic
- Apply federated learning or differential privacy techniques as needed to satisfy multi-tenant data isolation requirements across client contracts
- Maintain model versioning and experiment tracking (Azure ML or equivalent)
- Document model architecture, training decisions, and evaluation results for internal IP and governance records
Requirements:
- 5+ years of machine learning engineering experience with structured/tabular data
- Proficiency in Python, scikit-learn, XGBoost/LightGBM, and Azure ML or equivalent MLOps platforms
- Experience working with healthcare claims data or insurance data is strongly preferred
- Familiarity with multi-tenant or privacy-constrained ML environments
- Strong analytical thinking and ability to communicate model behavior to non-technical stakeholders
- Comfortable operating in a HIPAA-regulated environment with PHI handling restrictions
Share resume to [Confidential Information] / +91 9924488801
