Data Scientist, Fraud Risk
Owns data science and decisioning for onboarding fraud, identity, and KYC, developing predictive models, experiments, vendor evaluations, and monitoring systems. Requires 5+ years in data science or risk analytics, strong Python and SQL, and experience with adversarial classification problems.
About the job
Responsibilities
- Own and improve onboarding fraud decisioning across identity verification, KYC controls, application fraud models, policy rules, decline and verification waterfalls, and manual-review strategies.
- Build, validate, deploy, and monitor models detecting identity theft, synthetic identity, first-party fraud, and coordinated application abuse.
- Evaluate third-party fraud and identity vendors, including scores, attributes, lift, coverage, stability, latency, and cost.
- Design and analyze A/B tests, shadow tests, holdouts, and champion/challenger strategies.
- Investigate emerging fraud patterns and decision misses; develop features, rules, models, and review strategies.
- Build monitoring and AI-powered workflows for model drift, population shifts, vendor degradation, data-quality issues, and new attack patterns.
- Partner with Fraud Operations, Product, Engineering, Compliance, and Credit Strategy to productionize changes and communicate recommendations.
Requirements
- 5–8+ years of experience in data science, risk analytics, or a related quantitative field.
- Strong Python and SQL skills, including modeling, data transformation, and dataset creation from complex financial data.
- Experience building and evaluating predictive models for fraud, identity, KYC, AML, credit risk, trust and safety, or other adversarial classification problems.
- 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 using fraud capture, loss rate, false-positive rate, approval impact, verification friction, operational workload, and economic value.
- Ability to trace decisions through raw inputs, vendor responses, model scores, policy rules, and downstream outcomes.
- Experience owning projects from problem definition and exploratory analysis through production implementation, monitoring, and impact measurement.
- Ability to communicate complex analytical findings and tradeoffs to technical and non-technical audiences.
- Comfort using AI tools for analysis, investigation, feature development, documentation, and monitoring.
Nice to Have
- Experience with application or onboarding fraud, identity theft, synthetic identity, first-party fraud, application manipulation, or fraud rings.
- Familiarity with KYC, CIP, identity verification, document verification, device intelligence, behavioral signals, consortium data, credit bureau data, or alternative data sources.
- Experience evaluating and integrating third-party fraud or identity vendors.
- Experience with real-time scoring, decision engines, rules platforms, APIs, or production machine learning systems.
- Experience partnering with fraud operations or investigations teams.
- Familiarity with credit card underwriting, consumer lending, or regulated financial products.
- Experience with graph, anomaly-detection, or weakly supervised methods for coordinated or emerging fraud patterns.
Technology
- Python
- SQL
- Snowflake
- AWS
- Dashboarding and monitoring tools
Compensation and Benefits
- Competitive compensation and equity packages.
- Flexible paid time off.
- Fully covered healthcare, including dependent coverage.
- One Medical access and an optional FSA.
- 20 weeks of paid parental leave for the primary caregiver and 8 weeks for other new parents.
- Technology resources across business units.
Skills
Python, SQL, Snowflake, AWS, Machine Learning, Model Validation, Feature Engineering, Statistical Inference, A/B Testing, Fraud Detection, Identity Verification, Kyc, AML, Model Monitoring, Anomaly Detection
Similar jobs
Data Science jobs
Akur8
New York, NYThe Pricing Actuary leads client proof-of-concepts, applies P&C ratemaking expertise, and translates insurance requirements into software-driven solutions. The role requires at least five years of pricing experience, strong rate-filing knowledge, and familiarity with predictive modeling and machine learning.
Clay
San Francisco, CA
The Data Scientist will serve as an embedded analytical partner to product and business leaders, owning experimentation, causal inference, predictive modeling, and metric design. The role requires 5+ years of data science experience, expert SQL and Python, strong statistical foundations, and the ability to influence strategic decisions.
Zoox
Boston, MA
Develop datasets, performance metrics, and statistical methods to verify and validate an autonomous driving perception stack. The role requires advanced education in a quantitative field and proficiency in Python, SQL or Spark/Scala, exploratory analysis, visualization, and statistical modeling.
Rula
United States
The Data Scientist will analyze healthcare claims, billing patterns, and complex datasets to identify anomalies and support Trust & Safety, compliance, and legal operations. The role requires 5+ years of experience, expert SQL and Python/R skills, data visualization expertise, and strong risk-focused communication.
Decagon
San Francisco, CA
Senior individual contributor responsible for defining, operationalizing, and improving performance metrics for enterprise AI agent deployments. The role combines customer-facing advisory work, quantitative analysis, experimentation, and building scalable measurement tools and frameworks.