Specialty
The role
Mercury, a fintech company, is hiring a Senior Machine Learning Operations Engineer for its new Machine Learning Platform team. The role builds real-time model serving, deployment and monitoring for risk and fraud decisions. Location limits are not stated.
What you will do
- Build and run the low-latency, highly available real-time inference service for the risk decision engine
- Own model deployment infrastructure: registry, versioning and CI/CD with checks, shadow mode and staged rollouts
- Build model observability for availability, latency, errors and drift
- Work with Risk Data Science on handoff from development to production
- Add champion/challenger, canary routing and SHAP explainability
What they ask for
- 5+ years in ML engineering, backend engineering, MLOps or a related field
- Experience deploying and operating models in low-latency, high-availability settings
- Strong Python backend skills with FastAPI or Flask
- Experience with model registries, CI/CD for models and staged rollouts
- Experience with observability and alerting for production services
- SQL, Redis or DynamoDB and streaming such as Kafka or Kinesis
What they offer
- Base salary, equity (stock options or RSUs) and benefits
This is our own short reading of the posting. The full description, and anything that has changed since, is on Mercury's careers page behind the apply button.
