Postdoctoral Researcher – Scientific Machine Learning & Computational Chemistry

LBL; California (MO); Hybrid; USD 99,000 - 114,000; Full time

Job summary

Lawrence Berkeley National Laboratory (Berkeley Lab) seeks a Postdoctoral Researcher in Scientific Machine Learning & Computational Chemistry to advance ML methods for excited-state molecular dynamics and computational chemistry. You will develop physics-informed, symmetry-aware models, evaluate them on energy-relevant systems, and connect them to nonadiabatic workflows and open-source tools.

The role emphasizes hands-on software development, rigorous validation, and collaboration across diverse

Qualifications

• PhD in Computer Science, Computational Science, Chemistry, Physics, Applied Mathematics, Materials Science, Chemical Engineering, or related field.
• Strong Python with PyTorch or JAX.
• Experience applying ML to scientific/atomistic data.
• Knowledge of graph neural networks and symmetry-aware models.
• Ability to develop reliable research software in Linux with version control.

Responsibilities

• Conduct fundamental research in physics-informed and symmetry-aware ML for nonadiabatic excited-state dynamics.
• Develop equivariant GNNs and related architectures for multi-state PES learning.
• Design data-generation, active learning, transfer learning, and uncertainty analyses to reduce data costs.
• Implement and maintain open-source Python/JAX software; integrate models with nonadiabatic workflows and simulation interfaces.
• Publish results in peer-reviewed journals and contribute to software releases and collaborations.

Skills

Python programming

PyTorch

JAX

Graph neural networks

Linux environment

Education

PhD degree (last 3 years)

Tools

DeepMD

NEXMD

i-PI

MixPI

NWChem

CP2K

Job description

The Applied Mathematics and Computational Research Division at Lawrence Berkeley National Laboratory (Berkeley Lab) is seeking a Postdoctoral Researcher — Scientific Machine Learning & Computational Chemistry to conduct fundamental and applied research at the intersection of machine learning and computational chemistry. In this role, you will develop physics-informed, symmetry-aware models that accelerate excited-state simulations, integrate them into open-source scientific workflows, and validate their accuracy and performance on energy-relevant molecular and materials systems. You will also create robust, open-source implementations and connect the resulting models to nonadiabatic molecular dynamics simulation workflows.

We’re here for the same mission, to bring science solutions to the world. Join our team and YOU will play a supporting role in our goal to address global challenges! Have a high level of impact and work for an organization associated with 17 Nobel Prizes!

You will:

• Conduct fundamental research in physics-informed and symmetry-aware machine learning for nonadiabatic excited-state molecular dynamics.
• Develop and evaluate equivariant graph neural networks and related architectures that learn multiple-state adiabatic potential-energy surfaces, energies, gradients or forces, derivative nonadiabatic couplings, and state-transition behavior from electronic-structure data.
• Design reliable data-generation and training workflows, including sampling, active learning, transfer learning, validation, and uncertainty or robustness analysis, to reduce the cost of generating excited-state training data.
• Implement, test, document, and maintain research software; integrate trained models with surface-hopping and related nonadiabatic or path-integral workflows and with relevant simulation-code interfaces.
• Plan controlled ablation studies and reproducible evaluations using scratch training across multiple seeds, exact train and validation metrics, parity and error analyses, gradient checks, and end-to-end GPU timing; document limitations and extrapolation behavior.
• Implement, test, document, and maintain open-source Python/JAX research software; collaborate with researchers to connect trained models to DeepMD, NEXMD, i-PI, MixPI, or related nonadiabatic and path-integral workflows and validate.
• Publish results in peer-reviewed journals, present at scientific conferences and project meetings, contribute to software releases and reports, and mentor or collaborate with students and researchers as appropriate.

We are looking for:

• PhD degree, within the last 3 years, in Computer Science, Computational Science, Chemistry, Physics, Applied Mathematics, Materials Science, Chemical Engineering, or a related technical field.
• Demonstrated research experience in machine learning or deep learning for scientific or atomistic data, computational chemistry, computational physics, or a closely related area, with the ability to work across disciplinary boundaries.
• Strong Python programming skills and experience developing, training, and evaluating neural-network models with a modern framework such as PyTorch or JAX.
• Knowledge of graph neural networks, geometric deep learning, invariant or equivariant models, or related approaches for learning from molecular or physical systems.
• Ability to develop reliable research software in a Linux environment using version control, testing, documentation, and reproducible computational workflows.
• Record of scientific publication or presentation; ability to conduct independent research, work effectively in a highly collaborative multi-institutional environment, and communicate clearly in written and oral form.

Desired skills/knowledge:

• Experience with excited-state electronic-structure theory, nonadiabatic dynamics, surface hopping, path-integral methods.
• Experience with active learning, transfer learning, uncertainty quantification, multitask learning, or learning from sparse and expensive scientific data.
• Familiarity with atomistic or molecular-simulation software and interfaces, such as DeepMD, NEXMD, i-PI, MixPI, NWChem, CP2K, or comparable packages.
• Experience with GPU acceleration, distributed training, high-performance computing systems, or C/C scientific software development.

Additional information:

• Application date: Priority consideration will be given to candidates who apply by October 1, 2026. Applications will be accepted until the job posting is removed.
• Appointment type: This is a full-time, 2 year, postdoctoral appointment with the possibility of renewal based upon satisfactory job performance, continuing availability of funds and ongoing operational needs. You must have less than 3 years of paid postdoctoral experience. Salary for Postdoctoral positions depends on years of experience post-degree.
• Salary range: The salary range for this position is $8,827 – $10,233 and is expected to start at $8,827 or above. Postdoctoral positions are paid on a step schedule per union contract and salaries will be predetermined based on postdoctoral step rates. Each step represents one full year of completed post-Ph.D. postdoctoral experience.
• Background check: This position is subject to a background check. Any convictions will be evaluated to determine if they directly relate to the responsibilities and requirements of the position. Having a conviction history will not automatically disqualify an applicant from being considered for employment.
• Work modality: Work may be performed on-site, hybrid, full-time telework. The primary location for this role is Lawrence Berkeley National Lab, 1 Cyclotron Road, Berkeley, CA. Work must be performed within the United States. A REAL ID or other acceptable form of identification is required to access Berkeley Lab sites (for more information).
• Work authorization: Candidates must be eligible to work in the U.S. at the time of hire. Visa sponsorship is not available for this position.
• Union Represented: This position is represented by a union for collective bargaining purposes.

Why join Berkeley Lab?

We invest in our postdoctoral scholars by offering benefits and resources designed to support your well-being, professional growth, and life outside of work:

• Comprehensive health benefits, including medical, dental, and vision coverage
• 24 days of Personal Time Off (PTO) per fiscal year, plus sick leave and paid holidays
• Opportunities to connect, network, and grow through the Berkeley Lab Postdoc Association, including social events, professional development, and scientific exchange
• A collaborative and inclusive culture where you can grow your research career and belong

Equal Employment Opportunity Employer:

The foundation of Berkeley Lab is our Stewardship Values: Team Science, Service, Trust, Innovation, and Respect; and we strive to build community with these shared values and commitments. Berkeley Lab is an Equal Opportunity Employer. We heartily welcome applications from all who could contribute to the Lab’s mission of leading scientific discovery, excellence, and professionalism. In support of our rich global community, all qualified applicants will be considered for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, age, protected veteran status, or other protected categories under State and Federal law.

Misconduct Disclosure Requirement:

As a condition of employment, the final candidate who accepts an offer of employment will be required to disclose if they have been subject to any final administrative or judicial decisions within the last seven years determining that they committed any misconduct; or have filed an appeal of a finding of substantiated misconduct with a previous employer. For additional information,