This position is within the Advanced Light Source (ALS) Accelerator Physics Group (APG), part of the Accelerator Technology & Applied Physics (ATAP) Division. The APG is responsible for ensuring the operation, performance, and continuous improvement of the ALS accelerator complex.
The role advances artificial intelligence and machine learning for accelerator operations, spanning both applied research and the software that puts it into practice. The objective is to develop AI/ML methods, and the software that supports them, that make the ALS accelerator accessible to modern AI systems - enabling real-time machine optimization, AI-assisted operations, and intelligent automation of accelerator tuning and diagnostics. The work combines investigation of new approaches with their deployment in an operational environment.
The person in this position will connect accelerator control systems with modern AI/ML capabilities, supporting both existing optimization tools and next-generation autonomous agent systems for accelerator operations. The role is especially timely with the upcoming ALS Upgrade (ALS-U) commissioning, which offers the opportunity to establish these methods and tools correctly from the start.
You will:- Conduct applied research in artificial intelligence and machine learning methods for accelerator optimization, diagnostics, and operations.
- Develop and deploy machine learning models and autonomous AI agent systems for accelerator optimization, diagnostics, and operations.
- Design and develop the software and interfaces that connect accelerator control systems with AI/ML applications.
- Contribute to the group's software and computing environment, including control-system integration and operational tools.
- Collaborate with accelerator physicists, controls engineers, and operations staff to identify opportunities for automation and to translate physics requirements into working solutions.
- Disseminate results through publications in peer-reviewed journals and presentations at relevant conferences and workshops.
- Apply sound development practices to produce reliable, well-documented, and maintainable software.
- Support the operation of the ALS accelerator systems, including availability during off-hours as needed.
- Participate in the commissioning activities of the ALS Upgrade as they relate to AI/ML systems.
- Comply with LBNL/ALS Environment, Safety, and Health (EH&S) practices and requirements.
We are looking for:- Master's degree in computer science, physics, engineering, or a related field with at least 3 years of related experience; or a Bachelor's degree with at least 5 years; or an equivalent combination of education and experience. A Ph.D. in a relevant field is preferred and counts toward the experience requirement.
- Demonstrated experience developing and deploying software systems in a scientific or engineering environment.
- Strong programming skills, including proficiency in Python and familiarity with modern development practices (version control, testing, documentation).
- Working knowledge of machine learning methods and their application to scientific or engineering problems.
- Demonstrated ability to design and build complex software systems.
- Ability to work effectively in a multidisciplinary team alongside physicists, engineers, and operations staff.
- Good command of written and oral English and communication skills.
- Ability to foster constructive, respectful, and cooperative workplace relationships.
Desired skills/knowledge:- Experience working at an accelerator facility or similar large-scale scientific instrumentation environment.
- Experience with accelerator control systems (e.g., EPICS) and real-time data acquisition.
- Experience with machine learning frameworks (e.g., PyTorch, TensorFlow) and scientific computing libraries (e.g., NumPy, pandas).
- Familiarity with accelerator control system frameworks (e.g., EPICS, Bluesky, ophyd) and real-time data systems.
- Experience with LLM-based agent architectures, tool-use patterns, and autonomous AI systems.
- Experience with containerization (Docker), CI/CD pipelines, and production deployment practices.
- Experience with distributed systems, API design, and real-time data streaming.
Additional information:- Application date: Priority consideration will be given to candidates who apply by July 2, 2026. Applications will be accepted until the job posting is removed.
- Appointment type: This is a full-time career appointment, non-exempt (hourly paid), eligible for overtime pay.
- Salary range: The full salary range for this position is $9,761/month to $16,473/month and is expected to pay between the targeted range of $9,761 to $13,422/month. Salary for this position will be commensurate with the final candidate's qualification and experience, including skills, knowledge, relevant education, certifications, and aligned with the internal peer group. It is not typical for an individual to be offered a salary at or near the top of the range for a position.
- 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: This position is eligible for a hybrid work schedule - a combination of teleworking and performing work on site at Lawrence Berkeley National Lab, 1 Cyclotron Road, Berkeley, CA. Work schedules are dependent on business needs. Individuals working a hybrid schedule must reside within 150 miles of Berkeley Lab.
