Data Scientist (Credit) – Car Finance

Overview

In this role you will be at the heart of Marshmallow’s car-finance decisioning, shaping who gets credit and at what price. You’ll work with a small, high-performing team to build explainable, fair models that combine bureau, Open Banking and internal data for new-to-UK and thin-file customers. You’ll own end-to-end model development, from framing questions to live deployment in the decision engine, with immediate impact on lending decisions. This opportunity leverages AI-enabled processes to move faster and improve risk and customer outcomes. You’ll collaborate across engineers and a Head of Credit to scale a new lending platform focused on accessibility and transparency.

Pay / Benefits

• Bonus scheme designed to reward high performance
• Private medical insurance with Vitality
• Mental health support with Oliva
• Personal learning budget and 2 dedicated L&D days a year
• Monthly flexible benefits budget
• 25 days holiday plus bank holidays

Responsibilities

• Build, validate and monitor application and behavioural scorecards using bureau, Open Banking and internal data
• Design, test and refine credit strategy including cut-offs, affordability rules, pricing tiers and limits
• Run experiments and champion tests to validate policy/model changes before scaling
• Explore new data sources and signals and assess their use in decisioning
• Support model governance: document work, demonstrate fairness, and meet regulatory obligations (Consumer Duty, CONC, model risk)
• Collaborate with engineers to deploy models/rules into production and leverage AI tooling to accelerate work

Key requirements

• 2–5 years of experience in decision science or data science within consumer lending or regulated financial services
• Hands-on experience developing/refining credit scorecards or risk models (logistic regression and/or gradient boosting) including sample design, binning, reject inference, validation and monitoring
• Experience with Open Banking or other alternative data in credit decisioning
• SQL proficiency and ability to work with large, imperfect datasets
• Solid grounding in statistics and ability to gauge real vs. spurious results
• Commercial judgement: translate model output into lending decisions and explain trade-offs to non-technical audiences
• Curiosity and ownership—willingness to ship and iterate

• Curiosity
• Ownership
• Strong communication to explain trade-offs to non-technical audiences
• Credit scorecards and risk models (logistic regression, gradient boosting)
• Open Banking or alternative data in credit decisioning
• SQL and handling large datasets

…