Team description
The AI AML Engineering Squad sits at the intersection of machine learning and financial crime prevention, building the data products and ML systems that keep SumUp's transaction monitoring effective and compliant across 37 markets. This role carries genuine ownership: you'll be responsible for the models, pipelines, and risk scoring that determine whether suspicious activity is caught, escalated, and documented in a way that satisfies regulators. If you're motivated by technical depth, real-world impact, and the challenge of making ML work reliably in a high-stakes environment, this is built for you.
What you'll do
- Build, maintain, and improve ML models and batch training pipelines for AML transaction monitoring, focusing on detection quality, operational efficiency, and regulatory compliance
- Engineer Feature Store features mapped to AML typologies and suspicious behaviours, working closely with AML 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 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
- Strong Python skills with hands-on data engineering experience and a proven track record of building reliable, production-grade ML workflows
- Experience in feature engineering and unsupervised machine learning, with the ability to translate domain knowledge into model behaviours and alerting logic
- Proven ability to productionalise ML applications and operate end-to-end pipelines, including monitoring, versioning, and rollback in regulated environments
- Comfort working across complex, multi-source data ecosystems where data quality, lineage, and root-cause analysis require careful attention
- Clear communication skills with the ability to align cross-functional stakeholders, set expectations, and turn ambiguous compliance needs into a concrete technical plan