The Accelerator Physics Group (APG) of the Advanced Light Source (ALS), within the Accelerator Technology & Applied Physics (ATAP) Division at Lawrence Berkeley National Laboratory, is seeking a
Postdoctoral Researcher to develop artificial intelligence (AI) and machine learning methods for accelerator physics and operations.
You will combine physics-based simulation, digital twins, surrogate modeling, and statistical analysis of machine data to support optimization, diagnostics, and operational decision-making. The research will address how models calibrated against machine data, together with uncertainty quantification, can support reliable AI-driven workflows, tested in simulation and validated through beam studies. These models and workflows will be integrated into Osprey, the agentic AI platform developed at the ALS, so that agents can use them to analyze, optimize, and operate the accelerator under human oversight. The position is part of MOAT-Core, a multi-laboratory DOE Genesis Mission program focused on AI-driven accelerator facilities. In collaboration with the Osprey team and partner laboratories, you will develop and validate shared capabilities for use across the consortium. The position offers significant international visibility, with close collaboration with partner laboratories in the United States and abroad and opportunities to present results at leading conferences in accelerator physics and AI.
You will:- Conduct applied research on machine learning methods for accelerator physics and operations, including digital twins, surrogate modeling, model calibration against machine data, statistical data analysis, and uncertainty quantification.
- Build and maintain digital twins and virtual accelerators of the ALS and ALS-U, connecting physics simulation codes with live and archived machine data.
- Develop and evaluate agentic AI workflows in which agents use digital twins and machine data to plan, carry out, and analyze optimization tasks and beam studies.
- Develop AI-driven operations workflows (optimization, diagnostics, anomaly detection, data analysis, and decision support) and validate them in simulation before deployment on the machine.
- Carry out beam studies and machine-development shifts to validate models and automated workflows on the ALS.
- Integrate models and operations workflows into Osprey as validated tools that AI agents can use in accelerator operations.
- Package methods and workflows so that partner facilities in the MOAT-Core consortium can adopt them.
- Apply sound development practices (testing, CI/CD, documentation, code review) to produce reliable, maintainable open-source software.
- Disseminate research findings through peer-reviewed publications, conference presentations, workshops, and collaboration meetings.
- Participate in ALS-U commissioning activities as they relate to modeling and AI-driven operations.
- Comply with LBNL/ALS Environment, Safety, and Health (EH&S) practices and requirements.
- Contribute to a respectful and collaborative work environment.
We are looking for:- Ph.D. in physics, accelerator physics, or a closely related field, awarded within the last 3 years or expected before the appointment start date.
- Less than 3 years of paid postdoctoral experience.
- Research experience applying machine learning methods to physics, engineering, or scientific problems.
- Solid knowledge of the fundamentals of accelerator physics.
- Proficiency in Python and scientific computing, with solid software engineering skills (version control, testing, documentation).
- Ability to use AI coding tools effectively and critically, including reviewing and validating generated code.
- Working knowledge of machine learning, statistical inference, and optimization methods.
- Ability to work independently and effectively in a multidisciplinary team of physicists, software engineers, controls engineers, and operations staff.
- Good written and oral communication skills; ability to present research results effectively.
- Ability to foster constructive, respectful, and cooperative workplace relationships.
Desired skills/knowledge:- Experience with charged-particle beam dynamics and accelerator simulation codes (e.g., Elegant, Xsuite, Bmad, ImpactX, or similar).
- Experience with surrogate models, digital twins, or model calibration against experimental data.
- Experience with beam-based measurements at an accelerator facility, preferably a synchrotron light source.
- Experience with ML frameworks (e.g., PyTorch, JAX) and differentiable simulation.
- Familiarity with accelerator control systems (e.g., EPICS) and archived machine data.
- Experience with LLM-based agents or agentic workflows for scientific facilities.
Additional information:- Application date: Priority consideration will be given to candidates who apply by November 30, 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: This position is represented by a union for collective bargaining purposes. The salary range for this position is $5,957 - $9,234/month and is expected to start at $8,266/month or above based on a step schedule. 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 will be primarily performed 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 (for more information click here).
Want to learn more about working at Berkeley Lab? Please visit: careers.lbl.gov
