Senior Machine Learning Operations Engineer

📋 Description

• Build real-time inference service for risk scoring with low latency and high availability.
• Own deployment infra: registry/versioning, CI/CD with tests, shadow and staged rollouts.
• Build model observability: availability, latency, errors, and drift-triggered retraining.
• Partner with Risk Data Science for dev-to-prod handoffs to production under MLP.
• Implement experiments (champion/challenger, canary) and SHAP explainability.
• Own projects end-to-end; help shape and build a new platform team.

🎯 Requirements

• 5+ years in ML engineering, backend software, or MLOps.
• Production ML service experience deploying/serving models in low-latency, high-availability contexts.
• Strong Python backend fundamentals with FastAPI or Flask.
• Experience with model deployment tooling: registries, CI/CD, versioning, staged rollouts.
• Experience building observability/alerts for production services; drift signals.
• Comfort with SQL, low-latency stores (Redis/DynamoDB), and streaming (Kafka/Kinesis).

🎁 Benefits

• Remote or hybrid work options.
• Diversity and belonging emphasis.
• Accommodations available for applicants with disabilities.