• Operationalize key data science solutions that enable risk‑prediction products across underwriting, pricing, claims routing, and marketing. • Design and build ML pipelines using industry best practices, primarily leveraging AWS services like SageMaker, and integrating with tools such as MLflow for experiment tracking and data platforms like Snowflake. • Stand‑up and operate a shared feature store (Snowflake Snowpark + Kafka) that supports both batch and real‑time feature retrieval. • Own real‑time inference services, exposing low‑latency endpoints (SageMaker endpoints or EKS micro‑services) and managing blue/green or canary deployments. • Implement comprehensive testing strategies (including Unit, integration, data validation, model validation, and performance testing) within robust CI/CD pipelines to maintain high platform quality. • Enable ML Governance: Manage ML models and data versioning, experiment tracking, and reproducibility. • Implement event‑driven orchestration that triggers automated retraining, evaluation, and redeployment based on data drift or business events. • Monitor production models for performance, drift, and data quality—and drive automated remediation.