About the role

You’ll build and ship the machine-learning models behind Fluxo Risk, protecting thousands of businesses from fraud and abuse.

What you’ll do

• Develop real-time fraud models trained on billions of payments

• Design features from network, device and behavioral signals

• Run experiments that balance fraud loss with conversion

• Partner with engineering to ship models to production

What we’re looking for

• 4+ years in applied machine learning or data science

• Strong Python and SQL

• Experience deploying models with real-time latency budgets

Nice to have

• Fraud, credit or risk modeling experience

• Familiarity with graph-based methods

How we hire

A 30-minute intro call, a practical exercise reviewed together, and a final conversation with the team. Most processes take under three weeks.