About the Role



We are seeking a Data Engineer to join our Geospatial Data Science team supporting commodities trading. In this role, you will build and maintain the data pipelines and geospatial infrastructure that will, for example, turn raw vessel-movement data (AIS), port activity, and cargo flows into actionable trading signals across energy, agricultural, and metals markets.



You will work at the intersection of large-scale geospatial engineering and front-office trading, collaborating closely with portfolio managers, quantitative researchers, and fellow data scientists to deliver clean, reliable, and timely maritime datasets that directly inform investment decisions.




What You'll Do

• Design, build, and maintain robust ETL/ELT pipelines ingesting AIS and other maritime datasets (port calls, drafts, cargo, vessel metadata) at scale.

• Develop and optimize geospatial data models in PostGIS to support vessel tracking, route inference, port congestion, and storage/flow estimation.

• Write performant, well-tested Python and SQL to transform raw feeds into research- and trading-ready datasets.

• Engineer features and metrics (e.g., tonne-miles, floating storage, port dwell times, voyage estimates) in partnership with researchers and PMs.

• Ensure data quality, lineage, monitoring, and reliability across all maritime data products.

• Collaborate with the commodities desk to translate trading questions into data solutions.




Must-Haves

• 3+ years of commercial Python 3 experience - strong, production-quality coding skills (not just scripting).

• PostGIS- proficiency with spatial queries, indexing, and geospatial data modeling.

• AIS datasets- hands-on familiarity with vessel-tracking data, its structure, quirks, and limitations.

• SQL- strong proficiency, including query optimization on large datasets.




Nice-to-Haves

• Apache Airflow (or equivalent orchestration) for scheduling and managing pipelines.

• AWS experience (Azure or GCP equally welcome).

• Machine Learning experience, particularly applied to geospatial or time-series problems.

• Commodity trading exposure or understanding of how maritime data drives commodity markets.

• Containerization- Docker / Kubernetes for reproducible, deployable pipelines.

• GeoPandas- for geospatial data manipulation and analysis in Python.

• Domain knowledge of shipping- vessel classes, charter markets, freight rates, and IMO regulations.