Computational Chemist - Machine Learned Force Fields, Material Discovery
Core
Design and deploy machine learned force fields (MLFFs) to screen candidate molecules for PFAS-free semiconductor manufacturing materials, bridging quantum chemistry simulations and industrial validation.
Role type
Senior IC machine learning scientist (computational chemistry)
Builds
Machine learned interatomic potentials and automated data generation pipelines for materials discovery
Domain
Semiconductor manufacturing / Computational Chemistry / Machine Learning
Deliverable
production ML models
Required skills
Machine learned interatomic potentials, quantum chemistry (DFT), molecular dynamics, Python, PyTorch/JAX, cloud/HPC workflows, classical force fields, model validation
Preferred skills
Fluorine chemistry, thermodynamic cycle calculations, transport properties
Technologies
VASP, Quantum ESPRESSO, CP2K, ORCA, Psi4, Gaussian, MACE, NequIP, Allegro, TensorNet, DeePMD, LAMMPS, GROMACS, OpenMM, ASE
Responsibilities
Design high-throughput quantum chemistry campaigns to generate training data; build automated data generation infrastructure on cloud/HPC; train and deploy MLFFs for PFAS substitution; validate property predictions against reference data; extend potentials to condensed phase chemistries; run production prediction campaigns; collaborate with experimental partners to validate predictions.
Seniority
Senior, hands-on IC