Team Description
The Risk AI Engineering Squad is a cross-functional team within the Risk & Compliance tribe, responsible for developing cutting-edge data products and ML solutions that power Transaction Monitoring and protect SumUp's merchant base from Money Laundering and Financial Crime. We combine automation, AI, and engineering excellence to build innovative products that empower Risk and AML teams to work smarter, faster, and more efficiently.
The Senior Data Scientist role is critical to advancing transaction monitoring capabilities through machine learning, feature engineering, and scalable model pipelines. You will work across the full model lifecycle — from typology understanding and data exploration to feature development, training, validation, deployment, and monitoring — helping ensure Risk and AML controls remain effective, auditable, and compliant across products and markets.
SumUp actively welcomes applications from women and people from underrepresented backgrounds. Diverse perspectives make the team stronger and systems more robust. If you're motivated by technical depth, real-world impact, and the challenge of making ML work reliably in a high-stakes environment, this role is built for you.
What you'll do
- Build and ship production ML systems end to end: own and evolve end-to-end batch training pipelines, model versioning, monitoring, model deployment, and rollback for transaction monitoring models.
- Build, maintain, and improve ML models for transaction monitoring, focusing on detection quality, operational efficiency, and regulatory compliance.
- Engineer features mapped to AML and Fraud typologies and suspicious behaviours, working closely with Risk investigators to translate domain knowledge into alerting logic and threshold calibration.
- Run sensitivity tests on synthetic datasets, produce ML governance artefacts such as model cards, and deliver audit-ready documentation to meet regulatory expectations.
- Own and evolve the AML Risk Score by analysing driver contributions, monitoring drift, running back-testing, and recommending improvements to features, logic, and thresholds.
- Partner with AML and Fraud Operations, Product, and Engineering to translate stakeholder needs into actionable, scalable data science solutions.
- Track and improve detection performance metrics, adapt solutions to regional compliance requirements, and contribute to system design documentation.
You'll be great for this role if you have…
Must have
- Production Python engineering: you write code that ships — you're comfortable with CI/CD, automated testing, versioning, and monitoring in a real production environment.
- End-to-end ML pipeline experience: demonstrated experience deploying and operating ML models in production, including drift monitoring and rollback.
- Modelling and productionalizing models: demonstrated experience training ML models, choosing appropriate KPIs and metrics for evaluation.
- Data engineering fundamentals: hands-on experience with complex, multi-source data ecosystems, data quality, and lineage.
- Clear, confident communication: ability to align cross-functional stakeholders, set expectations, and turn ambiguous compliance requirements into a concrete technical plan.
Nice to have
- Experience with Pyspark.
- Experience in AML, fraud detection, or financial crime domains.
- Unsupervised machine learning (e.g. anomaly detection, clustering).
- Familiarity with Feature Stores and alerting threshold calibration.
- Experience producing regulatory ML governance artefacts (model cards, audit documentation).
- Experience with AI systems and tooling.