Co-Op, AI-Driven Equation Discovery

What you'll do

• Build equation-discovery pipelines and benchmark symbolic regression methods on experimental datasets.
• Design evaluation harnesses and apply equation discovery to electrochemistry, formulation, and materials data.
• Integrate discovered equations into models and digital twins, and communicate findings across research and science teams.

What they ask for

• Pursuing a Master's or PhD in ML, CS, applied math, physics, materials science, or chemical engineering.
• Strong Python skills and hands-on experience with PyTorch, JAX, or similar.
• Experience applying machine learning to real-world scientific or experimental data.
• Grounding in linear algebra, calculus, and probability; able to read and implement ML research methods.

Nice to have

• Working knowledge of symbolic or sparse regression methods such as SINDy, PySR, or PDE-FIND.
• Experience with LLM-guided symbolic regression, physics-informed ML, uncertainty quantification, operator learning, or digital twin workflows.

Tools

Python, PyTorch, JAX, SINDy, PDE-FIND, PySR, LLM-guided search, PINNs

AI focus

AI-driven equation discovery from experimental data, including symbolic regression, evaluation, and integration into surrogate models, physics-informed models, and experimental digital twins.