Senior Data Engineer – Risk & Compliance (CNP Protect)

Berlin, Germany | Full-time | Office-first

Team description

CNP Protect is a cross-functional squad within SumUp's Risk & Compliance tribe, responsible for the ML models, rule checkpoints, and automated decisioning systems that prevent card-not-present fraud at scale. We're currently executing two of the most technically demanding data engineering workstreams in the tribe: migrating from a third-party rules engine (NOTO) to a fully in-house system, and productionising a foundational merchant embedding model built on representation learning. This Senior Data Engineer will own the data layer that makes both possible — the feature pipelines, the embedding infrastructure, and the quality standards that underpin every automated decision we make.

What you'll do

• Build and operate Python and PySpark-based feature pipelines that serve enriched transaction and merchant attributes to our in-house rule engine and ML models, covering both batch and near-real-time processing
• Implement and standardise our Feature Store setup — defining schemas, ownership, freshness SLAs, and lineage documentation so attributes are consistent and auditable across rule engine and ML use cases
• Design and run batch pipelines to generate, version, and publish merchant embeddings using open table formats such as Apache Iceberg or Delta Lake, in collaboration with Data Science and ML Platform
• Put robust data quality in place across all pipelines: automated validation, monitoring, alerting, and end-to-end debugging from source through transformation to serving
• Collaborate with Risk Platform and Data Platform teams to adopt shared tooling and standards across orchestration, observability, and governance — and help the squad move toward near-real-time embedding serving

You'll be great for this role if…

• Advanced proficiency in Python and performance-tuned PySpark, with strong software engineering skills, including CI/CD for data applications in large-scale production environments
• Experience building and maintaining feature store pipelines, with hands-on knowledge of enriched attribute design for both online and offline serving
• Solid knowledge of AWS services, including S3, EKS, Keyspaces, and Athena, alongside open table formats such as Apache Iceberg or Delta Lake
• Familiarity with streaming and event-driven architectures — ideally Kafka — and a good grasp of API design, Docker, and Git-based version control workflows
• Experience with embeddings or representation learning pipelines is a strong plus, as is a background in fraud, risk, or other decisioning-heavy domains

Why you should join SumUp

• Opportunity to work with SumUppers globally on large-scale fintech products used by millions of businesses worldwide, from our Berlin office. This involves an office-first setup
• Commitment to Diversity and Inclusion: Be part of a workplace that values and promotes diversity, fostering an inclusive environment where everyone's perspectives are respected and embraced
• Enrolment in our Virtual Stock Option programme: you will own a stake in SumUp's future success
• A dedicated annual L&D budget of €2000 for your individual development, whic