Lead data engineer - ml pipelines

Das ist der Job

Decentriq is the rising leader in data-clean-room technology.

Darum lohnt es sich

With Decentriq, advertisers, retailers, and publishers securely collaborate on 1st-party data for optimal audience targeting and campaign measurement. Headquartered in Zürich, Decentriq is trusted by renowned institutions in the DACH market and beyond, such as RTL Ad Alliance, Publicis Media, and Post Finance.

Our analytics & ML pipelines are the heartbeat of this platform. Built in Python (pandas) and Apache Spark, they run either in Databricks workspaces or on our own Spark clusters deployed inside confidential-computing enclaves.

We are looking for a Senior Data Engineer (≥ 80 %, start as soon as possible) to take end-to-end ownership of these pipelines, raise their resilience to the next level, and push the boundaries of privacy-preserving machine-learning for Ad Tech. The role can be fully remote (± 4 h CET) or based in our Zürich/Berlin office.

Would you like to help us make the advertising industry ready for the 1st-party era? Then we’d love to hear from you! Tasks Own, Design & Operate Data Pipelines – Take full responsibility for all pandas- and Spark-based pipelines, from development through production and monitoring.

Advance our ML Models – Improve and productionise models for Ad Tech use-cases such as look-a-like modelling, audience expansion, and campaign measurement. Engineer for the Invisible – Because data inside confidential enclaves is literally invisible (even to root), build extra-robust validat