Chemical Physics (Enhanced Sampling, MLIPs)

Role overview Develop computational methods and software for molecular and materials prediction, combining molecular simulation, enhanced sampling, free energy calculations, and machine learning interatomic potentials. The work spans scientific research and implementation, taking methods from theoretical ideas through to scalable code.

Responsibilities - Lead or contribute to molecular dynamics, enhanced sampling, and free energy projects. - Develop and deploy accurate force fields and neural network potentials. - Build deep learning models for molecular and materials prediction. - Write efficient scientific software in Python or C++. - Turn theoretical methods into scalable implementations.

Requirements - PhD in chemical physics, chemistry, physics, materials science, or a related field. - Strong background in molecular dynamics, enhanced sampling, and free energy methods. - Experience developing force fields or neural network potentials and applying deep learning to molecular systems. - Proficiency in scientific programming.

Nice to have - Experience with electronic structure methods such as DFT, statistical mechanics, or rare-event methods. - Familiarity with parallel computing tools. - Experience with OpenMM, OpenFE, or training machine learning interatomic potentials such as MACE.

Benefits and work setup - Full-time role; the Bay Area is preferred, with exceptional remote candidates considered. - The source describes substantial equity for an early technical contributor.