Postdoc in Scientific ML for Excited-State Chemistry

Lawrence Berkeley National Laboratory

San Francisco (CA)

Hybrid

USD 106,000 - 123,000

Full time

14 days+

Application generator

Turn this role into an interview — a resume and cover letter built around what this employer wants.

Get past ATS filters

Job summary

Lawrence Berkeley National Laboratory in the United States seeks a Postdoctoral Researcher focused on Scientific Machine Learning and Computational Chemistry. You will develop physics-informed, symmetry-aware models to accelerate excited-state simulations and connect them to nonadiabatic molecular dynamics workflows.

You will publish in peer-reviewed journals, contribute to software releases, and collaborate across institutions.

Qualifications

PhD completed within the last 3 years in a relevant technical field.
Experience in machine learning for scientific or atomistic data.
Strong Python programming skills with PyTorch or JAX.
Knowledge of graph neural networks or equivariant models for molecular/physical systems.
Ability to develop reliable research software in Linux with version control, testing, and reproducible workflows.
Track record of scientific publications or presentations; ability to collaborate.

Responsibilities

Conduct physics-informed and symmetry-aware ML for nonadiabatic excited-state molecular dynamics.
Develop equivariant graph neural networks learning multi-state potential-energy surfaces, energies, gradients, and forces.
Design data-generation and training workflows including active learning and uncertainty analysis.
Implement and maintain open-source Python/JAX software; connect models to nonadiabatic workflows and simulation interfaces.
Publish results in peer-reviewed journals and mentor researchers.