Responsibilities
- Apply MLIPs (MACE, M3GNet, NequIP, GAP) to predict properties of materials
- Run atomistic simulations using DFT codes (VASP, Quantum ESPRESSO, CASTEP, etc.) and MD packages (LAMMPS, GROMACS, etc.)
- Implement graph neural networks and diffusion models to generate and optimize electrolyte candidates
- Perform synthesis prediction and precursor selection, linking atomistic modeling to experimental feasibility
- Curate and query large-scale materials and reaction databases for training and validation
Collaborate with experimental teams to validate predictions and feed results back into automated workflows
Requirements
- PhD in Materials Science, Chemistry, Physics, or related field
Demonstrated experience with MLIPs (MACE, M3GNet, NequIP, etc.)
- Proficiency with DFT codes (VASP, QE, CASTEP, etc.) and MD engines (LAMMPS, GROMACS, etc.)
- Experience with ASE, pymatgen or similar toolkits for job setup/automation
- Strong skills in Python and building scientific workflows
- Knowledge of synthesis prediction, precursor selection, or cheminformatics
- Strong database and automation framework skills (Fireworks, Jobflow, Atomate, Airflow, Temporal)