Data Scientist, Fraud Risk

In the U.S., co-branded cards alone account for over $300 billion in annual spend, and most still run on decades-old legacy bank systems. Imprint is the modern alternative: flexible, embeddable, and built for how people actually pay today. Backed by Kleiner Perkins, Thrive Capital, Ribbit, and Khosla Ventures, we're...

The Risk team at Imprint builds the models, policies, and analytical systems that protect our credit card programs while delivering a fast and seamless member experience.

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. Your goal will be to stop identity theft, synthetic identity, first-party fraud, and other forms of application abuse while minimizing ...

5 to 8+ years of experience in data science, risk analytics, or a related quantitative field, ideally at a high-growth startup or fintech company
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
Experience with application or onboarding fraud, including 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, including measuring incremental value relative to existing controls
Experience with real-time scoring, decision engines, rules platforms, APIs, or production ML systems
Experience partnering with fraud operations or investigations teams and converting case-review findings into scalable controls
Familiarity with credit card underwriting, consumer lending, or regulated financial products
Experience with graph, anomaly-detection, or weakly supervised methods for identifying coordinated or emerging fraud patterns
We don't expect every candidate to check every box. If this role excites you and you bring strong fundamentals, we encourage you to apply.
Stack
Python and SQL for modeling and analysis. Snowflake for data warehousing. AWS infrastructure. Dashboarding and monitoring tools for production systems.

Learn more about how we build at Imprint on our engineering blog: https://medium.com/imprint-eng