Postdoctoral Scholar - AI-Driven Materials Discovery at Lawrence Berkeley National Laboratory

University of Delaware; Berkeley (CA); On-site; USD 86,936 - 97,103; Full time

Benefits offered by this job

Competitive salary

Access to world-class HPC resources

Opportunity for renewal based on performance

Job summary

A leading research institution seeks a Postdoctoral Scholar in AI-Driven Materials Discovery. This role involves developing machine-learning interatomic potentials and collaborating with scientists on cutting-edge projects. Ideal candidates hold a Ph.D. and demonstrate expertise in ML models and DFT methods, along with a strong publication record. The position is on-site at Lawrence Berkeley Lab and offers a competitive salary. Apply by October 1, 2025 to contribute to innovative materials science research.

Qualifications

• Ph.D. in a relevant field required.
• Expertise in training machine learning models for materials science applications.
• Proficiency in Python and HPC environments.

Responsibilities

• Develop, train, and validate ML interatomic potentials.
• Build and optimize DFT workflows for property prediction.
• Collaborate with scientists to tackle materials science problems.

Skills

Training machine learning models

Strong publication record

Independent and collaborative work

Education

Ph.D. in Materials Science, Physics, Chemistry, Computer Science

Tools

Python

DFT methods (VASP, Quantum ESPRESSO, WIEN2k)

MLIP frameworks (NequIP, MACE, CHGNet, GAP, SNAP)

Job description

Postdoctoral Scholar - AI-Driven Materials Discovery

Lawrence Berkeley National Lab’s (LBNL) Energy Storage & Distributed Resources Division has an opening for a Postdoctoral Scholar in AI-Driven Materials Discovery to join the team. In this exciting role, you will play a pivotal role in an ambitious, multi-institutional, DOE‑funded effort to build the next generation of AI for scientific discovery. This position offers a unique opportunity to work at the frontier of computational materials science, combining machine‑learned interatomic potentials (MLIPs), density functional theory (DFT), and large‑scale machine learning on some of the world’s fastest supercomputers. The scholar will develop and train advanced ML models, design scalable autonomous simulation workflows, and contribute to multimodal AI systems that integrate physics, data, and reasoning. Working closely with collaborators across Berkeley Lab and partner institutions, the scholar will have access to world‑class HPC resources and the one‑of‑a‑kind A‑Lab automated synthesis facility, enabling research that bridges simulation and experiment. This position is ideal for a creative and highly skilled computational scientist eager to push the boundaries of AI‑driven materials discovery and establish themselves as a leader in the field.

What You Will Do:

• Develop, train, and validate machine‑learned interatomic potentials for a wide range of inorganic materials.
• Build and optimize high‑throughput DFT workflows for property prediction and benchmarking against MLIPs.
• Train and scale machine learning models on leadership‑class HPC resources (NERSC, ALCF, etc.) using parallel and distributed computing approaches.
• Contribute to the development of simulation agents that autonomously couple MLIPs, DFT, and molecular dynamics for multiscale modeling.
• Integrate computational results into multimodal foundation models and agentic AI frameworks developed within the overall project.
• Collaborate with computational and experimental scientists to address benchmark materials science problems.
• Publish results in peer‑reviewed journals, present at conferences, and contribute to open‑source software tools.

Additional Responsibilities as needed:

• Assist in outreach activities, workshops, and tutorials to disseminate project outcomes.

What is Required:

• Ph.D. in Materials Science, Physics, Chemistry, Computer Science, or a related field.
• Demonstrated expertise in training machine learning models, preferably for atomistic or materials science applications.
• Experience with MLIP frameworks (NequIP, MACE, CHGNet, GAP, SNAP) and integration with DFT.
• Strong background in DFT methods and workflows (VASP, Quantum ESPRESSO, WIEN2k).
• Proficiency in Python and experience with large‑scale parallelization and HPC environments.
• Strong publication record in computational materials science, AI/ML for science, or related fields.
• Ability to work independently as well as collaboratively within a large, multi‑institutional team. Note that this position will be on‑site.

Desired Qualifications:

• Experience with agentic AI or autonomous workflows for science.
• Familiarity with experimental data or integration of simulations with experimental workflows.
• Knowledge of molecular dynamics simulations and force field development (LAMMPS, ASE).
• Prior contributions to open‑source scientific software.

For consideration, please apply by October 1, 2025 with the following application materials:

• Cover Letter - Describe your interest in this position and the relevance of your background.
• Curriculum Vitae (CV) or Resume.

Notes:

• 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.
• This position is represented by a union for collective bargaining purposes.
• The monthly salary range for this position is $7,790 / mo - $8,701.00 / mo and is expected to start at $7,790 / mo 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 and/or related research experience. FY26 rates not determined yet.
• 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.
• This position is eligible for onsite only, at Lawrence Berkeley National Lab, 1 Cyclotron Road, Berkeley, CA. A REAL ID or other acceptable form of identification is required to access Berkeley Lab sites.

Want to learn more about working at Berkeley Lab? Please visit:

careers.lbl.gov

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.

Berkeley Lab is a University of California employer. It is the policy of the University of California to undertake affirmative action and anti‑discrimination efforts, consistent with its obligations as a Federal and State contractor.

Misconduct Disclosure Requirement: As a condition of employment, the finalist will be required to disclose if they are subject to any final administrative or judicial decisions within the last seven years determining that they committed any misconduct, are currently being investigated for misconduct, left a position during an investigation for alleged misconduct, or have filed an appeal with a previous employer.