Senior Data Scientist

About the Role

At SumUp, we're on a mission to empower small businesses across the globe by providing a vast set of simple and affordable business tools to help them start, run, and grow their businesses. Lending at SumUp is a mature, scaled business with a strong and proven credit risk foundation. Our core models and decisioning frameworks are already robust and in production; as our portfolio grows, our challenge is safely extracting marginal gains from a complex system where changes are incremental and the stakes are high. As a Senior Data Scientist, you will be highly hands-on and embedded in day-to-day lending decisions. This role exists to strengthen our ability to improve what already works, reduce operational risk, and ensure long-term reliability as we scale into new markets. You will work within the Credit Risk Analytics (CRA) team, a streamlined group responsible for the modeling and analytics that underpin our global lending portfolio.

What you'll do

• Optimise Credit Risk Models: Iterate on existing models to improve stability, predictive power, and net revenue impact while performing deep dives to support risk decisions.
• Drive End-to-End Deployment: Develop, test, and deploy new model versions in close collaboration with Credit Risk Engineering (CRE), ensuring no regressions or operational issues.
• Enhance ML Infrastructure: Improve machine learning pipelines and workflows to reduce maintenance overhead and failure modes.
• Integrate New Evaluate and integrate new internal and external data sources (e.g., credit bureaus, open banking) into existing models and processes.
• Monitor Performance: Closely monitor models in production, investigating performance shifts or anomalies to maintain portfolio integrity.
• Promote Technical Excellence: Document work clearly and participate in code reviews, design discussions, and pair programming to maintain high-quality standards.

What makes you great for this position

• 5+ years of experience as a Data Scientist (or 7+ years in data-related/software engineering fields with at least 3 years in Data Science).
• MUST HAVE experience working with Credit Risk. 
• Deep understanding of Data Science principles, including statistics, probability theory, and machine learning concepts.
• Strong experience with Python (pandas, PySpark, scikit-learn) and SQL for complex data retrieval and manipulation
• Proven track record of building, evaluating, and deploying machine learning models end-to-end at scale.
• Experience with credit risk assessment, lending, or financial decisioning models.
• Strong software engineering practices, including writing clean, maintainable, testable code with version control and documentation.
• Collaborative and respectful team player who is comfortable voicing disagreements while committing to team decisions (