Senior MLOps Engineer - Real-Time Inference Platform

Mercury.com; New York (NY); On-site; USD 167,000 - 208,000; Full time

Benefits offered by this job

Remote work

Job summary

Mercury is hiring a Senior Machine Learning Operations Engineer to build and operate the real-time inference service for risk decisions. You will own deployment infrastructure, observability, and experimentation features while partnering with Data Science to move models from development to production.

You will work on low-latency, high-availability ML services, shaping a brand-new platform team and driving end-to-end production readiness with CI/CD, shadow/champion rollout, and SHAP

Qualifications

• 5+ years in ML engineering, backend engineering, MLOps, or related field.
• Production ML service experience: deploying, serving, and operating models in low-latency, high-availability contexts.
• Strong Python backend fundamentals with APIs (FastAPI/Flask).
• Experience with model deployment lifecycles: registries, CI/CD, versioning, staged rollout (shadow/canary).
• Experience building observability and alerting for production services, incl. drift signals.
• Familiar with data stores and streaming (SQL, Redis, DynamoDB, Kafka/Kinesis/Redpanda).

Responsibilities

• Build and operate the real-time inference service for the risk engine.
• Own model deployment infrastructure: registry, versioning, CI/CD, rollout patterns.
• Build model observability: latency, errors, drift detection.
• Collaborate with Risk Data Science to move models to production.
• Implement experimentation: champion/challenger, canary, explainability outputs (SHAP).
• Shape and own a brand-new platform team.

Skills

ML Engineering

Backend Engineering

MLOps

Production ML

CI/CD

Observability

Tools

Python

FastAPI

Flask

SQL

Redis

DynamoDB

Kafka

Job description

Mercury is hiring a Senior Machine Learning Operations Engineer to build and operate the real-time inference service for risk decisions. You will own deployment infrastructure, observability, and experimentation features while partnering with Data Science to move models from development to production.

You will work on low-latency, high-availability ML services, shaping a brand-new platform team and driving end-to-end production readiness with CI/CD, shadow/champion rollout, and SHAP