Senior Data Engineer - Risk & Compliance (CNP Protect)

About

In this role, you design and maintain production-grade data pipelines powering ML workflows for card-not-present fraud protection. You own data quality, reliability, and governance, and help expand our data foundations and feature store governance. You collaborate with risk, ML data, software, and analytics teams to deliver safe production changes. You will work in a mission-driven fintech team that uses real-time data processing and emerging embeddings to strengthen fraud detection.

Responsibilities

• Design, build, and maintain production-grade Python-based data pipelines for ML workflows and real-time data processing
• Own data quality and reliability with validations, automated testing, monitoring, and SLAs
• Document architecture, data lineage, dataset definitions, and dependency management
• Lead feature store governance, improve usability, and standardise feature store setup for faster, confident data science work
• Collaborate with Risk Platform, ML Data Platform, data scientists, software engineers, and analysts to deploy changes to production

Requirements

• Strong proficiency in Python and PySpark
• Experience building and maintaining feature engineering pipelines for online and offline use cases
• Cloud experience (AWS: S3, EKS, Keyspaces, Athena) and containerisation (Docker) with Git version control
• Experience with streaming/event-driven architectures (Kafka) and open table formats (Apache Iceberg or Delta Lake)
• Track record of data quality and governance with clear communication to non-technical stakeholders

Benefits

• Virtual Stock Option programme
• Annual L&D budget (2000)
• Corporate pension scheme (up to 20%)
• 28 days paid leave + holidays
• Urban Sports Club subsidy
• Kita placement assistance