ML Ops Engineer

Sourced from feeny.ai

Coinflow, a Chicago-based payments infrastructure company, is hiring an MLOps Engineer to own the platform that brings fraud, risk, and payments models from notebook to production. You'll build real-time inference, feature pipelines, deployment tooling, and monitoring for models that sit directly in the transaction authorization path. The role emphasizes latency, reliability, and explainability, with AI-native tooling used as a force multiplier.

• Build and operate the real-time inference layer that scores transactions in the authorization path
• Own end-to-end training, validation, and deployment pipelines and a reproducible feature store
• Implement model versioning, registries, shadow mode, champion/challenger, canary rollouts, and rollback
• Instrument models for latency, score distributions, feature drift, and fraud/chargeback outcomes
• Integrate and evaluate third-party fraud and risk vendor models via parallel and shadow testing
• Power data and scoring behind merchant-facing risk tooling

• 4+ years in MLOps, ML infrastructure, or ML platform engineering, ideally in fintech or a regulated environment
• Experience running models in production with real latency and uptime requirements
• Strong Python and solid production engineering habits; comfortable with TypeScript/Node
• Hands-on experience with ML pipeline and serving tooling such as MLflow, Kubeflow, SageMaker, Vertex, BentoML, or Feast
• Infrastructure skills: containers, Kubernetes, CI/CD, and a major cloud provider
• Data engineering experience building reliable feature pipelines and understanding training/serving skew
• Experience monitoring models in production: drift, calibration, and business outcome metrics
• Familiarity with fraud, risk, or credit modeling and explaining model behavior to non-ML stakeholders

• Experience with real-time inference in a transaction or decisioning path
• Comfort with AI-native tooling such as Claude Code as a daily driver
• A bias toward shipping working v1s quickly