Data scientist jobs in New York, NY

About the role

As a Data Scientist focused on Onboarding Fraud, you will own the modeling and analytics that power fraud and identity decisions from application submission through account opening. You will partner closely with Fraud Strategy and Operations, Product, Engineering, Compliance, and Credit Strategy to improve onboarding fraud and KYC decisioning. You will build models, evaluate third-party fraud and identity vendors, test new scores and attributes, design experiments, and translate emerging fraud patterns into scalable policy changes. You will also build monitoring and AI-powered analytical workflows that detect shifts, diagnose root causes, and help the team respond quickly as fraud tactics evolve.

What you'll bring

• 5 to 8+ years of experience in data science, risk analytics, or a related quantitative field
• Strong Python and SQL skills, with the ability to build models, transform raw data, and create custom datasets from complex financial data
• Experience building and evaluating predictive models for fraud, identity, KYC, AML, credit risk, trust and safety, or another adversarial classification problem
• Strong understanding of supervised machine learning, model validation, backtesting, calibration, feature engineering, and production model monitoring
• Deep understanding of statistical inference and experiment design, including A/B tests, holdouts, champion/challenger tests, causal measurement, and tradeoff analysis
• Ability to evaluate decision systems—not just model performance—using metrics such as fraud capture, loss rate, false-positive rate, approval impact, verification friction, operational workload, and economic value
• Full-stack problem-solving orientation: you can trace a decision through raw inputs, vendor responses, model scores, policy rules, and downstream outcomes to find the root cause of a problem
• Comfort owning projects end-to-end, from problem definition and exploratory analysis through production implementation, monitoring, and business impact measurement
• Ability to communicate complex analytical findings and decision tradeoffs clearly to technical and non-technical audiences
• Comfort using AI tools to accelerate analysis, investigation, feature development, documentation, and monitoring—and excitement about building AI-powered risk systems
• Stack
• Experience with application or onboarding fraud, including identity theft, synthetic identity, first-party fraud, application manipulation, or fraud rings

Benefits

Locations