Machine Learning Physics Graduate Student
Core
Develop parallel C/C++/Python codes to train, test, and evolve partial differential equations (PDEs) and interatomic potentials for modeling material behavior at continuum and atomic scales.
Role type
Graduate student intern in machine learning for materials science
Builds
Machine learning interatomic potentials and discovered PDEs for phase field models
Domain
Materials Science / Physics / Applied Mathematics
Deliverable
production ML models | research
Required skills
C/C++ programming, Python programming, parallel computing, numerical solutions of partial differential equations, materials science background, physics background
Preferred skills
GPU code porting, experience with phase field models, publication record
Technologies
C, C++, Python, GPUs
Responsibilities
Develop parallel codes to train and evolve PDEs and interatomic potentials, analyze results, review literature, document results and write papers, present work at poster sessions
Seniority
Graduate student (intern)
