MLOps Engineer

You will own the platform that moves fraud, risk, and payments models from notebooks into production. You will build real-time serving, training and feature pipelines, safe deployment workflows, monitoring, vendor integrations, and risk-product data and scoring capabilities.

Responsibilities

• Build and operate real-time model-serving infrastructure
• Build end-to-end training, validation, deployment, and feature pipelines
• Manage model versioning, registries, shadow mode, champion-challenger testing, canary rollouts, and rollback
• Monitor latency, score distributions, feature drift, approvals, fraud, and chargeback outcomes
• Integrate and evaluate third-party fraud and risk models
• Build data and scoring capabilities for merchant-facing risk products

Requirements

• 4+ years of MLOps, ML infrastructure, or ML platform engineering experience
• Experience running production models with latency and uptime requirements
• Strong Python skills
• Ability to read and write TypeScript and Node
• Experience with ML pipeline and serving tools such as MLflow, Kubeflow, SageMaker, Vertex, BentoML, or Feast
• Infrastructure skills in containers, Kubernetes, CI/CD, and a major cloud provider
• Data engineering experience with operational, warehouse, and streaming data
• Knowledge of training-serving skew, model drift, and calibration
• Familiarity with fraud, risk, or credit modeling
• Experience with AI-native tooling or willingness to use it

Benefits

• Equity grant
• Health and wellness benefits
• 401(k) savings plan
• Flexible time off