Senior Data Scientist, Fraud Analytics — Build In-House ML

Unchain Data; San Francisco (CA); On-site; USD 153,000 - 205,000; Full time

Job summary

Circle is seeking a Senior Data Scientist on Fraud Analytics to own the prediction loop, turning labels into features and models while moving from vendor scores to Circle's in-house models.

You will partner with Fraud Strategy, Fraud Operations, Risk Engineering, and Compliance to build end-to-end detection for onboarding, login, and money movement, leveraging advanced Python/SQL and rigorous evaluation.

Qualifications

• 5+ years in data science or applied ML in fraud, risk, or financial crime.
• Advanced Python and SQL with experience in XGBoost/LightGBM.
• Experience with sparse, delayed, or biased labels, including cold start, reject inference, and chargeback lag.
• Strong statistics: anomaly detection, graph or network methods, experimentation, and threshold optimization.
• Experience taking models to production and monitoring them.
• Clear communication with technical and non-technical partners.
• Ability to work through ambiguity and limited historical data.

Responsibilities

• Build and evaluate fraud models for onboarding, login, account changes, and money movement. Target risks include account takeover, scams, money mules, and stolen and synthetic identity.
• Evaluate third-party risk signals and design the path from vendor models to Circle models, from shadow mode to production.
• Define the label taxonomy and data requirements with Fraud Operations and Risk Engineering, so every event, decision, and outcome becomes training data. This includes the fraud we miss.
• Design holdout and exploration sampling to measure false negatives and the rate at which we wrongly block good customers.
• Track fraud rate, dispute rate, fraud loss rate, and precision across customer segments. Help set thresholds against an agreed loss budget.
• Work with Fraud Strategy to tune thresholds and rules and respond to emerging attacks.
• Backtest, monitor drift, and retrain models on Circle's fraud platform.
• Help build AI agent workflows for transaction review, fraud-ring analysis, and rule drafting, and evaluate their accuracy against human labels.

Skills

Python

SQL

XGBoost

LightGBM

Fraud domain

Statistics

Production ML

Communication

Ambiguity tolerance

Job description

Circle is seeking a Senior Data Scientist on Fraud Analytics to own the prediction loop, turning labels into features and models while moving from vendor scores to Circle's in-house models.

You will partner with Fraud Strategy, Fraud Operations, Risk Engineering, and Compliance to build end-to-end detection for onboarding, login, and money movement, leveraging advanced Python/SQL and rigorous evaluation.