Data Scientist, Risk

About Imprint

Imprint is creating a platform that helps leading brands improve customer lifetime value. The company began with co-branded credit cards and has reimagined them to be smarter, more rewarding, and centered around each brand. Its partners include Crate & Barrel, Rakuten, Booking.com, H-E-B, Fetch, and Shell, among others. Imprint helps launch modern credit products that strengthen loyalty, create savings, and support growth.

Beyond the card itself, the company blends modern payments infrastructure, advanced underwriting, and rich customer data to anticipate customer behavior and respond in real time. That allows brands to launch strong financial products without needing to become a bank.

Co-branded cards represent more than $300 billion in annual U.S. spending, yet most still rely on older bank infrastructure. Imprint positions itself as a flexible, modern alternative built for how people pay today. The company is backed by Kleiner Perkins, Thrive Capital, Ribbit, and Khosla Ventures.

Role Overview

The Risk team is focused on making credit decisions that are both faster and more intelligent, while still protecting credit quality. The team develops the models, policies, and analytical systems that support underwriting, fraud detection, and portfolio performance across Imprint’s credit programs.

As a Data Scientist, Risk, you will own the modeling behind top-of-funnel credit decisioning, starting at application intake and continuing through approval across every acquisition channel. These channels include direct affiliates such as Credit Karma and NerdWallet, invitation-to-apply email, direct mail, paid social, instant prescreens, and on-site applications.

Your core objective will be to increase approvals without weakening risk standards. You will improve underwriting models, design policy tests, and identify segments where credit access can be safely broadened. This role sits at the intersection of credit strategy and acquisition strategy.

You will work closely with Credit Strategy, Product, Engineering, and Marketing to build channel targeting models, assess channel performance, and tie acquisition volume to downstream economics such as approval rates, vintage loss forecasts, lifetime value, customer acquisition cost, and contribution profit. Over time, the work will also involve building AI-enabled systems that can monitor approvals and channel behavior, detect shifts, diagnose issues, and recommend policy changes automatically.

What Success Looks Like in the First 90 Days

• Launched a model or policy update in production that improves approval rates while keeping credit quality intact.
• Completed a detailed review of the approval funnel, highlighting the biggest opportunities to expand approvals safely by channel, segment, or score range, with a clear link to acquisition economics such as LTV/CAC and contribution profit.
• Built or improved a targeting model for at least one acquisition channel, such as affiliate, invitation-to-apply, or prescreen, together with Credit Strategy and Marketing.

Responsibilities

• Manage and enhance the full top-of-funnel credit decisioning pipeline, including application scoring, policy rules, decline waterfalls, and approval-rate optimization across acquisition channels.
• Create and refine underwriting and targeting models, including credit scoring, segmentation, and propensity models, to increase safe approvals and improve acquisition quality by channel.
• Define targeting rules and risk frameworks for new and emerging channels such as affiliates, invitation-to-apply, direct mail, instant prescreens, and paid social, working with Credit Strategy and Marketing.
• Plan and evaluate A/B tests and champion/challenger experiments for credit policy changes, with structured readouts covering both acquisition and credit outcomes.
• Use statistical inference, causal methods, and experiment design to separate policy effects from population changes and shifts in channel mix.
• Create channel-level performance models that translate application volume into credit outcomes including approval rates, expected losses, LTV, CAC, LTV-to-CAC, and contribution profit.
• Build monitoring tools that surface approval-rate anomalies, score drift, and shifts in population mix, then identify likely causes and next actions.
• Develop segmentation approaches that uncover underserved groups where credit access can be expanded responsibly.
• Design agentic workflows that automate parts of the risk analytics process, including funnel diagnostics, model monitoring, and policy simulation.

Requirements

• 5 to 8+ years of experience in data science, risk analytics, or another quantitative field, ideally in a high-growth startup or fintech environment.
• A degree in statistics, mathematics, engineering, economics, computer science, or a similar relevant discipline.
• Strong Python and SQL ability, including model building, data transformation, and creation of custom datasets from complex financial data.
• Hands-on experience with credit risk or targeting models such as scorecards, underwriting models, or segmentation, or comparable predictive modeling in a regulated setting.
• Strong grasp of statistical inference, experimentation design, and causal analysis.
• Analytical thinking with a bias toward action and strong attention to numerical accuracy.
• Clear communication skills, with the ability to explain complex results to both technical and non-technical audiences, including senior leaders and partners.
• Comfort managing projects end to end and working cross-functionally with Policy, Strategy, Product, and Engineering.
• Practical, full-stack problem-solving style and comfort digging into messy data, tracing issues to their source, and challenging assumptions.

Nice to Have

• Background in credit card underwriting, lending, or consumer credit products.
• Exposure to credit bureau data such as Vantage, FICO, and tradeline attributes, along with alternative data sources.
• Experience building or scaling experimentation infrastructure for credit policy testing.
• Familiarity with fraud detection, KYC/IDV workflows, or application fraud modeling.
• Understanding of acquisition channel economics and experience working with marketing or credit strategy on targeting.
• Knowledge of affiliate platforms, invitation-to-apply programs, instant prescreens, or direct mail targeting.
• Experience with model governance, regulatory documentation, or fair lending analysis.
• Background in time series analysis, forecasting, or optimization.
• Comfort with dashboarding tools.

Perks & Benefits

• Competitive pay and equity.
• Choice of a leading configured work computer.
• Flexible paid time off.
• Fully covered high-quality medical coverage, including dependent coverage.
• Additional health benefits including access to One Medical and the option to enroll in an FSA.
• 20 weeks of paid parental leave for the primary caregiver and 8 weeks for all new parents.
• Access to strong technology resources across the business, designed to support innovation, efficiency, and productivity.

Equal Opportunity

Imprint is committed to maintaining a diverse and inclusive workplace and is an equal opportunity employer. Employment decisions are made without regard to race, national origin, gender, gender identity, sexual orientation, protected veteran status, disability, age, or any other protected characteristic. The company welcomes people from all backgrounds who want to help build the future of payments and rewards.

Compensation

The stated salary range for this role is $170,000 to $220,000.