Co-Op, AI-Driven Equation Discovery
Core
Develop and benchmark methods to extract interpretable governing equations from high-throughput experimental data in electrochemistry, formulations, and advanced materials.
Role type
Co-op AI-driven equation discovery researcher
Builds
End-to-end equation discovery pipelines, symbolic regression models, and surrogate models for digital twins
Domain
Physical Sciences R&D, AI/ML, Electrochemistry, Materials Science
Deliverable
production ML models
Required skills
Python, PyTorch/JAX, symbolic regression, linear algebra, calculus, probability, reading ML research papers
Preferred skills
SINDy/PySR/PDE-FIND, LLM-guided symbolic regression, physics-informed ML, uncertainty quantification, operator learning, digital twin workflows
Technologies
PyTorch, JAX, SINDy, PDE-FIND, PySR, LLMs
Responsibilities
Build equation discovery pipelines, benchmark symbolic regression methods, apply discovery to live datasets, design evaluation harnesses, embed equations into surrogate models, document and present findings
Seniority
Co-op (Master's/PhD student)
