Postdoctoral Researchers in AI-driven atomistic modeling and AI-accelerated cheminformatics
Core
Developing AI-driven atomistic modeling and AI-accelerated cheminformatics to solve major global challenges in chemistry and materials science.
Role type
Postdoctoral Researcher in computational chemistry and materials science
Builds
Production ML models for interatomic potentials, high-throughput automated workflows, and data-driven molecular design
Domain
Computational chemistry, materials science, AI/ML
Deliverable
production ML models
Required skills
Machine-learning interatomic potentials, high-throughput automated workflows, atomistic modeling of material structures, simulation of molecular diffusion and interactions, atomistic simulation of chemical reactions, data-driven cheminformatics, molecular dynamics simulations
Preferred skills
Machine learning interatomic potentials (GAP, NNP, MTP, ACE, MACE), density functional theory studies, chemical reaction modeling, enhanced sampling, scripting (Python, bash), high-performance programming (Fortran/C/C++, CUDA), ML libraries (sklearn, Pytorch)
Technologies
GAP, NNP, MTP, ACE, MACE, LAMMPS, Gromacs, SMILES, Python, bash, Fortran, C, C++, CUDA, sklearn, Pytorch
Responsibilities
Develop machine-learning interatomic potentials; create high-throughput automated workflows for atomistic simulations; model molecular diffusion and interactions with surfaces/nanoporous media; simulate chemical reactions and thin-film growth; apply ML-based techniques to cheminformatics
Seniority
Postdoctoral, hands-on IC