Co-op, Machine Learning for Digital Twins

About the role#

As a Machine Learning Co-op for Digital Twins, you will contribute to the development of AI systems that accelerate discovery in the physical sciences. You will work within the Physical Sciences AI team to build digital twins of experimental campaigns, focusing on calibrated, uncertainty-aware models that improve the throughput and quality of experimental facilities. You will gain hands-on experience with operator learning, surrogate modeling, and uncertainty quantification, with your work directly informing the design and execution of scientific experiments.

What you'll do#

• Contribute to ML models for scientific and experimental systems, focusing on specific digital twin sub-problems.
• Build and train surrogate, operator-learning, or physics-informed models using experimental and simulation data.
• Calibrate models, quantify uncertainty, and validate results against data from active experimental campaigns.
• Translate open-ended scientific questions into concrete ML tasks with defined datasets, baselines, and evaluation criteria.
• Document findings and share results through write-ups and presentations in collaboration with cross-departmental teams.

What you'll need#

• Currently pursuing a Master's or PhD in Machine Learning, Computer Science, Applied Mathematics, Physics, or a related quantitative field (PhD preferred).
• Strong programming skills in Python and experience with ML frameworks such as PyTorch or TensorFlow.
• Experience applying machine learning to scientific, engineering, physical, or experimental systems.
• Familiarity with neural operators, operator learning, or scientific computing.
• Ability to work effectively with messy, heterogeneous, or evolving scientific datasets.

Location & details#

• Location: Cambridge, Massachusetts
• Modality: On-site
• Term: Rolling
• Status: Full-time, paid internship