About the role
- The Risk team at Imprint is responsible for making smarter, faster credit decisions that balance growth with responsible risk management
- The team builds the models, policies, and analytical systems that power underwriting, fraud detection, and portfolio optimization across all of Imprint’s credit programs
- As a Data Scientist, Risk, you will own the modeling powering Imprint’s top-of-funnel credit decisioning—from application intake through approval—across every acquisition channel: direct affiliates (Credit Karma, NerdWallet), invitation-to-apply emails, direct mail, paid social, instant prescreens, and on-site applications
- Your primary focus will be improving approval rates while maintaining credit quality: building better underwriting models, designing policy experiments, and uncovering segments where we can safely expand access to credit
- This role sits at the intersection of credit and acquisition strategy
- You will partner directly with Credit Strategy, Product, Engineering, and Marketing to build targeting models for new channels, evaluate channel-level credit performance, and connect acquisition volume to downstream economics—approval rates, vintage loss forecasts, LTV, CAC, and contribution profit
- Increasingly, that means building not just analyses but AI-powered systems that can autonomously monitor approval rate, channel performance, diagnose shifts, and recommend policy adjustments
- Own and improve the full top-of-funnel credit decisioning pipeline: application scoring, policy rules, decline waterfalls, and approval rate optimization across direct affiliates, invitation-to-apply, direct mail, paid social, instant prescreens, and on-site applications
- Build and iterate on underwriting, targeting, and segmentation models that expand safe approvals and improve channel-level acquisition quality
- Design and analyze A/B tests and champion/challenger experiments on credit policies, establishing a test-and-learn cadence with structured readouts on both acquisition and credit performance
- Build channel-level performance models that connect application volume to downstream economics: approval rates, expected losses, LTV, CAC, and contribution profit
- Design and build agentic workflows and AI-powered monitoring systems that autonomously detect approval rate anomalies, diagnose score drift and population mix changes, and recommend policy adjustments
- Partner directly with Credit Strategy, Product, Engineering, and Marketing to develop targeting criteria and risk frameworks for new and emerging acquisition channels
- Build segmentation frameworks to identify underserved populations where credit access can be responsibly expanded
- Stack:
- Python and SQL for modeling and analysis. Snowflake for data warehousing. AWS infrastructure. Dashboarding and monitoring tools for production systems
- 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
- Full-stack problem-solving orientation: you dive into messy data, trace a decline to its root cause, and question assumptions in pursuit of a better answer
- Comfort owning projects end-to-end in a fast-moving startup environment with limited scaffolding, collaborating cross-functionally with Policy, Strategy, Product, and Engineering
- Deep understanding of statistical inference, experimentation design, and causal analysis, with the ability to disentangle policy impact from population shifts and channel mix changes
- Comfort with AI tools and AI-native workflows; you actively use tools like Claude, Copilot, or similar to accelerate your work and are excited to build AI-powered analytical systems
- Ability to present complex findings clearly to technical and non-technical audiences, including senior leadership and external partner stakeholders
- Experience building credit risk or targeting models (scorecards, underwriting models, segmentation) or similar predictive modeling in a regulated environment
- 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
- Strong Python and SQL skills, with the ability to build models, transform raw data, and create custom datasets from complex financial data
- Experience with credit card underwriting, lending, or consumer credit products
- Familiarity with credit bureau data (Vantage, FICO, tradeline attributes) and alternative data sources
- Experience building or scaling experimentation infrastructure for credit policy testing
- Exposure to fraud detection, KYC/IDV workflows, or application fraud models
- Understanding of acquisition channel economics and experience partnering with marketing or credit strategy teams on targeting and LTV modeling