Commodities Data Engineer - AI-Driven ETL & Pipelines

Millennium Management LLC; Greater London; On-site; GBP 90,000 - 130,000; Full time

Job summary

Millennium is seeking a Data Engineer for Commodities to design, implement, and maintain end-to-end ETL pipelines that ingest data from multiple vendor and internal sources, using Python and SQL.

You will build standardized data models, schedule pipelines with Airflow, and implement validation and anomaly-detection controls while collaborating with portfolio managers, researchers, and data analysts to refine datasets and documentation.

Qualifications

• 5+ years of experience in data engineering, analytics engineering, or a similar role building and maintaining ETL pipelines.
• Strong Python and SQL skills, including experience working with large datasets and complex data transformations.
• Hands-on experience with Airflow or comparable workflow orchestration tools.
• Experience with Git, CI/CD pipelines such as GitHub Actions, and automated testing frameworks such as PyTest.
• Strong attention to detail, data quality, and documentation, with the ability to identify edge cases and protect data integrity.
• Ability to work independently, communicate effectively with technical and non-technical stakeholders, and manage multiple concurrent initiatives.
• Knowledge of commodities markets and data, including weather, supply and demand, storage, freight, or flows, is preferred.
• Experience with data warehousing, columnar storage formats, analytic databases, data catalog or governance tools, or financial services, trading, or research-driven environments is preferred.

Responsibilities

• Design, implement, and maintain end-to-end ETL workflows in Python and SQL to ingest and transform commodities data from multiple vendor and internal sources.
• Build and maintain standardized data models, schemas, and metadata that make commodities datasets easy to understand, discover, and reuse.
• Schedule, monitor, and manage data pipelines using Airflow or similar workflow orchestration tools to ensure reliable, timely data delivery.
• Implement validation, reconciliation, and anomaly-detection controls to maintain data completeness, accuracy, and consistency.
• Apply AI to automate schema inference across structured and semi-structured data sources, manage schema drift, and accelerate scalable ingestion development.
• Use AI-driven data-quality, observability, and documentation capabilities to detect anomalies, monitor data health, and produce clear lineage and technical documentation.
• Maintain high-quality, production-ready code and repeatable deployments through Git, GitHub Actions, PyTest, and automated testing practices.
• Partner with commodities Portfolio Managers, researchers, data analysts, and data strategists to refine datasets, definitions, and documentation based on evolving business needs.

Skills

Python

SQL

Airflow

Git CI/CD

PyTest

Data quality

Stakeholder comms

Independent work

Commodities data

Data warehousing

Job description

Millennium is seeking a Data Engineer for Commodities to design, implement, and maintain end-to-end ETL pipelines that ingest data from multiple vendor and internal sources, using Python and SQL.

You will build standardized data models, schedule pipelines with Airflow, and implement validation and anomaly-detection controls while collaborating with portfolio managers, researchers, and data analysts to refine datasets and documentation.