Senior Machine Learning Operations Engineer

Mercury is a fintech company focused on creating a safe banking experience for startups. The Senior Machine Learning Operations Engineer will build and operate the Machine Learning Platform’s production lifecycle, including real-time inference, model deployment, observability, experimentation, and retraining capabilities. The role partners with Risk Data Science to move models into reliable, low-latency, highly available production environments.

Responsibilities:

• Build and operate the real-time inference service that scores models for the risk decision engine, with low latency and high availability as first-class requirements
• Own model deployment infrastructure: registry and versioning, CI/CD with performance, bias, and consistency checks, shadow mode, and staged rollouts
• Build model observability: availability, latency, and error monitoring, plus drift detection as a retraining trigger
• Partner with Risk Data Science to take models from a clean development-to-production handoff through to production operation under MLP ownership
• Implement experimentation capabilities such as champion/challenger and canary routing, and explainability outputs like SHAP attributions
• Feel a strong sense of product ownership and actively seek responsibility. We self-organize on small and medium projects, and we want someone excited to help shape and build a brand-new platform team

Requirements:

• 5+ years in machine learning engineering, backend software engineering, MLOps, or a closely related field
• Production ML service experience: deploying, serving, and operating models in low-latency, high-availability contexts
• Strong backend engineering fundamentals in Python, with API frameworks like FastAPI or Flask
• Experience with model deployment and lifecycle tooling: model registries, CI/CD for models, versioning, and staged rollout patterns (shadow, canary, champion/challenger)
• Experience building observability and alerting for production services: latency, errors, and ideally model-specific signals like drift
• Comfort with the data layer ML depends on: SQL, key-value/low-latency stores (Redis, DynamoDB, or equivalent), and streaming pipelines (Kafka, Kinesis, Redpanda, or equivalent)
• Familiarity with a modern data stack (Snowflake, dbt, Dagster, Airflow, or similar)
• Experience operating in a regulated, audit-sensitive, or compliance-adjacent environment
• Exposure to functional languages or willingness to work across a stack that includes Haskell, React, and TypeScript