About the role
Responsibilities:
- Production APIs: Serve analytics and ML outputs across GCC deployments.
- ETL/ELT Pipelines: Feed workloads like supply chain forecasting, claims adjudication, and population health.
- Predictive Models: Build statistical/ML models for commodity flows, payer analytics, health indicators.
- Collaboration Translate clinical/operational questions into measurable data problems.
- Model Lifecycle: Monitor, retrain, and ensure data quality frameworks.
- Architecture Input: Extend lakehouse stack (Iceberg, ClickHouse, Parquet, Dagster, lakeFS, dbt).
- Coding Standards: Write clean, production-grade Python/SQL code.
Requirements:
- Experience: 6-9 years split between data science + backend/data engineering.
- Core Tech: Python (Pandas, NumPy, scikit-learn, SQLAlchemy, FastAPI), SQL, columnar DBs (ClickHouse preferred).
- Deployment: Proven track record of shipping and maintaining ML models in production.
- Event-Driven Systems: Kafka familiarity is a plus.
- Transformation Tools: dbt or equivalent; knowledge of medallion/lakehouse patterns.
- Domain Knowledge: FHIR, claims, supply chain, logistics (bonus differentiator).
- Context: Comfort in B2G environments with sovereignty, auditability, compliance.