Das ist der Job
This role focuses on the production ML lifecycle including deployment, real-time inference, and retraining.
Darum lohnt es sich
Mercury's ML platform team builds the paved path from model training to production deployment, ensuring reliability and observability. Total rewards include base salary, equity, and benefits.
The company is committed to creating a safe environment and values diversity, with a growing team focused on innovation. #J-18808-Ljbffr Key Responsibilities: Build and operate the real-time inference service for risk decision engine with low latency and high availability.
Own model deployment infrastructure including CI/CD, shadow mode, and staged rollouts. Build model observability and partner with Risk Data Science for production operation. Requirements: 5+ years in ML engineering, backend engineering, or MLOps with production ML service experience.
Strong Python and API framework skills, plus experience with model lifecycle tooling and observability. Familiarity with data layer technologies like SQL, key-value stores, and streaming pipelines. Compensation: Base salary range for US employees: $166,600 - $208,300; for Canadian employees: CAD 157,400 - 196,800.
Mercury Mercury is a fintech company that provides banking services for startups via partner banks.
