ML Engineer - Commodities Applied ML (Summer Internship - Master's)

Data Science is a key differentiator for BAM’s Commodities strategy. The ability to leverage data effectively is increasingly central to our investment process. The Commodities Data Science team applies advanced analytics, machine learning, and AI to develop tools, signals, and decision-support capabilities that help global Investment Teams improve investment outcomes.

As a ML Engineering Intern, you will complete a hands-on 10-week program focused on solving complex, real-world problems. You will gain firsthand experience applying data science and AI to support the commodities investment process. The internship begins with a training block covering the Commodities business and the investment process before you join the desk. You will also receive mentorship from senior team members, collaborate closely with peers, and build relationships across the broader intern cohort.

In this role, you will leverage BAM’s alternative datasets to develop practical geospatial analytics and data products. Projects may include satellite and aerial imagery analysis, meteorological and hydrological modeling, crop-yield forecasting, and other spatial data science applications.

You will work across the end-to-end development process: translating investment-team needs into analytical solutions; preparing and integrating data; developing, validating, and improving statistical and machine-learning models; and communicating results through clear, usable outputs for investment professionals and senior stakeholders.

Responsibilities:

Applied Analytics: Use structured and alternative data to solve commercially relevant problems for Commodities Investment Teams
Insights & Communication: Produce actionable insights through analysis, visualizations, dashboards, and concise written output to technical and non-technical audiences
Model Development: Build, validate, and improve statistical and machine-learning models and signals
Data Engineering: Develop reliable data pipelines and datasets for analytical and investment use cases
Production Deployment: Deploy and maintain data products with cloud-native architecture in mind
Teamwork & Mindset: Self-driven and results oriented. Perpetually curious while staying exceptionally organized and collaborative in a fast-paced, ambiguous environment

What you’ll do and what you’ll bring:

Partner with global commodities investment teams to turn investment ideas into questions that can be tested with data
Analyze market and alternative datasets to form independent, evidence-based views on investment hypotheses
Build statistical and machine learning models when they are the right tools for the research question
Practice robust modeling and backtest hygiene, including attention to data leakage, look-ahead bias, and overfitting
Write clear, reproducible Python and SQL that others can review, challenge, and build on
Present findings, assumptions, and uncertainties clearly to technical teammates and non-technical investors; listen to feedback and disagree constructively
Bring a strong foundation in statistics, machine learning, Python, and SQL, with familiarity with Git and development practices
Use LLMs and agents judiciously, verify their outputs, and be able to reason through problems without them