Founding ML Lead - Fraud & Risk Intelligence

Unchain Data; Chicago, Northern (IL, KY); Hybrid; USD 225,000 - 275,000; Full time

Benefits offered by this job

Competitive compensation

Equity grant

Health & wellness benefits

401(k) savings plan

Job summary

Coinflow in Chicago, IL seeks a Machine Learning Lead to own the fraud and risk intelligence layer of the platform. This founding ML role will lead the first dedicated ML team, combining transaction data with partner signals to optimize approvals, reduce fraud, and improve risk decisioning across geographies.

The ideal candidate has hands-on experience building fraud models in payments, exposure to the acquiring side, and a track record deploying production ML systems.

Qualifications

• 5+ years in machine learning, applied data science, or production ML roles.
• Experience building fraud models in payments on the acquiring side.
• Proven track record deploying ML projects to production.
• Deep familiarity with acquiring-side fraud dynamics: card-present/card-not-present, chargebacks.
• Strong foundation in ML, statistics, and feature engineering on high-volume financial data.
• Able to own ambiguous problems end-to-end and create structure.

Responsibilities

• Strengthen detection and risk decisioning capabilities—feature engineering, modeling, deployment.
• Own the full model lifecycle: experimentation, evaluation, monitoring, iteration.
• Define and track fraud metrics: detection rate, false positives, chargebacks, disputes.
• Explore data to surface new fraud signals and attack patterns.
• Collaborate with Engineering, Product, and Ops to embed fraud intelligence into payments.

Skills

Machine Learning

Data Science

Feature Engineering

High-Volume Data

Model Deployment

Team Collaboration

Tools

MLOps

Cloud Compute Planning

Fraud Analytics Tools

Job description

Coinflow in Chicago, IL seeks a Machine Learning Lead to own the fraud and risk intelligence layer of the platform. This founding ML role will lead the first dedicated ML team, combining transaction data with partner signals to optimize approvals, reduce fraud, and improve risk decisioning across geographies.

The ideal candidate has hands-on experience building fraud models in payments, exposure to the acquiring side, and a track record deploying production ML systems.