Senior Data Scientist

Circle • San Francisco, CA

3d • $152,500 - $205,000 • Remote

About The Position

As a Senior Data Scientist on Circle’s Fraud Analytics team, you will own the prediction side of Circle’s fraud loop. You will turn fraud labels into features and models, measure model accuracy, and help move Circle from third-party scores to in-house models. You will work with Fraud Strategy, Fraud Operations, Risk Engineering, and Compliance.

The role focuses on building and evaluating fraud models for onboarding, login, account changes, and money movement. Risks include account takeover, scams, money mules, and stolen or synthetic identity. You will help establish the data and labeling foundations needed to train models, evaluate third-party signals, measure false negatives and wrongly blocked customers, set thresholds against an agreed loss budget, and maintain model performance through backtesting, drift monitoring, and retraining. You will also help develop and evaluate AI agent workflows for transaction review, fraud-ring analysis, and rule drafting.

Requirements

• At least 5 years of experience in data science or applied machine learning focused on fraud, risk, or financial crime.
• Advanced Python and SQL skills, with experience using XGBoost, LightGBM, or similar tools.
• Experience building models with sparse, delayed, or biased labels, including cold start, reject inference, and chargeback lag.
• Strong statistical skills, including 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.
• Comfort working through ambiguity and limited historical data.

Nice To Haves

• Fintech, payments, crypto, or card fraud experience, including chargebacks and disputes.
• Experience with device intelligence, behavioral signals, or consortium data.
• Familiarity with blockchain analytics, AML, and KYC.
• Experience evaluating LLM or agent-based review workflows.

Responsibilities

• Build and evaluate fraud models for onboarding, login, account changes, and money movement, addressing account takeover, scams, money mules, and stolen and synthetic identity.
• Evaluate third-party risk signals and design the transition from vendor models to Circle models, from shadow mode to production.
• Define label taxonomy and data requirements with Fraud Operations and Risk Engineering so events, decisions, and outcomes—including missed fraud—become training data.
• Design holdout and exploration sampling to measure false negatives and the rate of wrongly blocking good customers.
• Track fraud rate, dispute rate, fraud loss rate, and precision across customer segments, and help set thresholds against an agreed loss budget.
• Work with Fraud Strategy to tune thresholds and rules and respond to emerging attacks.
• Backtest models, 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.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed