Data Scientist – iwocaPay Credit Risk Modelling

Overview

In this role you will own and evolve credit risk models for the iwocaPay BNPL product, shaping how we lend to SMEs. You’ll work closely with a small Risk Squad to build supervised ML models on tabular data, while developing data pipelines and production-ready solutions. You’ll influence the risk roadmap through model design and monitoring, collaborating with cross-functional teams. This is a hands-on, impact-driven role in a fast-moving fintech environment with a clear mission to enable responsible growth for SMEs.

Pay / Benefits

• Flexible working hours
• Medical insurance from Vitality
• Private GP service
• 25 days’ holiday per year
• One-month fully paid sabbatical after four years
• Employee equity incentive scheme

Responsibilities

• Co-own and review credit risk models for iwocaPay
• Develop supervised ML models on tabular data from end-to-end lifecycle (exploration, training, deployment, monitoring)
• Contribute to data engineering and pipeline development as the squad builds its own data flows
• Collaborate with other data science teams to test ideas and leverage transfer learning
• Shape the risk roadmap and define monitoring guidelines for the squad
• Design risk aspects for new products and lending features
• Evaluate model output and explain decisions for non-technical stakeholders

Key requirements

• Statistical foundations from a quantitative degree (probability, statistics)
• Production ML experience on tabular data (end-to-end in deployment and monitoring)
• Ability to work in a small, fast-moving team and own loosely defined problems
• Judgement to know when a model is ready for live deployment and how to iterate
• Experience using AI to accelerate delivery and build modelling pipelines or tools
• Strong communication to explain technical concepts to product, risk, and leadership
• Bonus: domain experience in credit risk or lending; non-linear methods; data engineering; coding in Python

• clear and concise written and verbal communication
• strong judgement and critical thinking
• collaboration in a cross-functional setting
• supervised ML on tabular data
• gradient boosting or neural networks for tabular data
• transfer learning or domain adaptation

…