Yingze Wang is a PhD candidate at UC Berkeley with five years of experience bridging theoretical and computational chemistry and applied machine learning. They focus on force field development and ML-driven interatomic models, bringing research-grade rigor to practical engineering problems. As an active contributor to the deepmodeling/dpgen project, Yingze integrated Gromacs with deep learning potentials (including deepmd-kit 2.0), added restart-from-checkpoint support, and resolved subtle issues in model-devi activation and charge-model handling. Based in Berkeley, they are adept at turning ML chemistry prototypes into robust, reproducible workflows.
The deep potential generator to generate a deep-learning based model of interatomic potential energy and force field
Role in this project:
ML Engineer
Contributions:6 reviews, 17 commits, 3 PRs in 1 month
Contributions summary:Yingze primarily contributed to enhancing the Gromacs engine within the deep potential generator, `dpgen`. Their work involved integrating Gromacs with deep learning models, including adding support for deepmd-kit 2.0 and different-charge model_devi systems. They also added support for various features, such as restarting from checkpoints, and fixed bugs related to model-devi activation functions and trajectory frequency.
Manipulating DeePMD-kit, VASP, LAMMPS data formats.
Contributions:14 PRs, 73 pushes in 6 months
linked-open-datalammpspythoncreditworkitem
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.