Realtime MLOps Engineer for Fraud & Payments

Coinflow; Chicago (IL); On-site; USD 120,000 - 180,000; Full time

Job summary

Coinflow is hiring an MLOps Engineer to own the platform that takes our fraud, risk, and payments models from notebook to production. You'll build pipelines, serving infra, and monitoring to score every transaction in real time, retrain safely.

Latency, reliability, and explainability matter as much as accuracy. You’ll work with AI-native tooling to automate pipelines, evals, and operations; if you want to shape ML infra at a fast-growing PSP, you’ll fit in.

Qualifications

• 4+ years in MLOps, ML infrastructure, or ML platform engineering.
• Experience with production ML systems in latency-sensitive environments.
• Strong Python and production engineering habits.
• Familiar with TypeScript/Node for services.
• Hands-on knowledge of ML tooling and feature stores.
• Solid infra skills: containers, Kubernetes, CI/CD, cloud.

Responsibilities

• Real-Time Model Serving: score transactions in the authorization path with low latency.
• ML Pipelines & Feature Store: end-to-end training, validation, deployment pipelines.
• Model Deployment & Rollout: versioning, canary rollouts, and safe rollbacks.
• Monitoring & Drift Detection: track latency, drift, and model metrics.
• Third-Party Model Integration: evaluate external fraud/risk vendors.
• Merchant-Facing Risk Tooling: power risk scoring for merchants.

Skills

MLOps experience

Real-time inference

Python

TypeScript/Node

CI/CD

Cloud platforms

Data pipelines

Model monitoring

Fraud modeling

AI-native tooling

Tools

MLflow

Kubeflow

SageMaker

Vertex AI

BentoML

Feast

Job description

Coinflow is hiring an MLOps Engineer to own the platform that takes our fraud, risk, and payments models from notebook to production. You'll build pipelines, serving infra, and monitoring to score every transaction in real time, retrain safely.

Latency, reliability, and explainability matter as much as accuracy. You’ll work with AI-native tooling to automate pipelines, evals, and operations; if you want to shape ML infra at a fast-growing PSP, you’ll fit in.