We are seeking a Data Scientist to transform operational data into the predictive models and insights that drive port performance. In this role, you will own the end-to-end analytical lifecycle — from sourcing and integrating data into our Azure Lakehouse to productionizing ML models and solvers using Databricks, dbt, and GitHub. You are a technical expert and a "data translator" who can navigate the full Medallion Architecture, ensuring that complex findings are converted into clear visualizations and actionable executive presentations. By leveraging advanced statistics and Generative AI, you will develop robust pipelines and dynamic tools that identify bottlenecks and provide high-quality, just-in-time solutions for our commercial and industrial stakeholders.
You’ll be part of a multifunctional analytics team, comprising data scientists, data stewards, data translators and analytics specialists. Beyond your direct team, you’ll be part of data communities and working groups, so you can learn and work together with likeminded colleagues from different departments and IT. As part of the Digital Port Performance team, you’ll also have close interaction with program managers, business managers and customers of the Port of Rotterdam.
Key responsibilities include:
- Source and integrate missing structured or unstructured data to fill operational visibility gaps, ensuring all ingestion follows established data governance and Medallion Architecture standards in the Azure Lakehouse.
- Develop and productionize explanatory and predictive models (such as regressions, ML models, or solvers), delivering from POCs in local notebooks to dbt models and GitHub-managed code following central CI/CD workflows.
- Engineer robust data pipelines using Databricks and dbt to ensure datasets are clean, accurate, and integrated for dynamic insight generation via Power BI, Genie AI/BI, and Databricks Dashboards.
- Act as a data translator, asking questions, aligning expectations and translating complex models and technical findings into clear visualizations and executive-level presentations for business and program managers.
- Collaborate across the value chain, working with architects and platform engineers upstream and Data Stewards/Specialists internally to continuously improve data infrastructure and port-wide standards.