Lawrence Berkeley National Laboratory - Physics

508 13029
Position ID:LBNLPhysics-Physics-COMPUTATIONALPHYSICSPOSTDOC [#13029, 86105]
Position Title: Postdoctoral Fellow
Position Type:Postdoctoral
Position Location:Berkeley, California 94720, United States [map]
Subject Areas: Physics / Accelerator and Beam Physics, Astrophysics (astro-ph), Astrophysics Experiment, Astrophysics Theory, Computational physics, Cosmology, HEP-Experiment (hep-ex), High Energy Experimental, High Energy Physics
Starting Date:2019/06/03
Appl Deadline:2019/01/31 11:59PMhelp popup finished (2018/12/19, finished 2019/08/04, listed until 2019/06/19)
Position Description:    

*** this position has been closed and new applications are no longer being accepted. ***

Berkeley Lab’s Computational Research Division has an opening for a Postdoctoral Scholar to assist in the implementation and documentation of new high-performance computing (HPC) approaches to a variety machine learning challenges in the Physical Sciences. Over the course of the last five years, LBNL’s Computing Research Division in collaboration with NERSC Data Analytics group and the Physics Division has developed a research program in data-driven pattern recognition algorithms for High Energy Physics (HEP) and Cosmology, targeting massively parallel and post-Moore architectures (including neuromorphic and quantum systems). Several promising research directions involve the development of distributed Geometric Deep Learning, algorithms based on distributed graph neural networks, as well as Generative Adversarial Networks.  


What You Will Do:

  • In the context of the ExaLearn Co-Design Center, will collaborate with LBNL physicists and computer scientists to develop innovative distributed pattern recognition algorithms for the next generation of HEP and Cosmology experiments and simulations on HPC systems.

  • Develop workflows for distributed training and optimization of graph neural networks, GANs and regression algorithms as we push to Exascale.

  • Investigate data and model parallelism approaches to train and run these on current HPC systems like ORNL Summit and NERSC 9.

  • Troubleshoot and solve problems of moderate scope and monitor benchmarks and bottlenecks in current codes and document these efforts.

Additional Responsibilities as needed:

  • May contribute to one or more existing research projects like CosmoFlow, CosmoGAN, and HEP.TrkX and HEP.QPR. The first three are dedicated the development of Machine Learning algorithms for Cosmology and HEP while the latter is focused on Quantum Computing Pattern Recognition algorithms for HEP experiments.

What is Required:

  • Applicants need to have a Ph.D. in data sciences, computer science, software engineering, applied physics, physics, astronomy or related fields.

  • Experience with modern data analytics and machine learning frameworks and libraries.

  • Research experience in solving machine learning problems and demonstrated expertise in python for scientific computing.

  • Background and experience in computational methods and scientific computing.

  • Background in physics, engineering, or computer science.

  • Excellent oral and written communication skills.

  • Demonstrated ability to work effectively as part of a cross-disciplinary team.

Additional Desired Qualifications:

  • Graph algorithms and libraries.

  • 3-D convolutions.

  • Pattern recognition.

  • HEP computing, cosmology data analysis, cosmological simulation.

  • Software performance evaluation and optimization.

  • HPC systems.

  • GPGPU programming.

  • C++.

The following required application materials listed below must be submitted through Academic Jobs Online:

  1. Curriculum Vitae.

  2. Cover Letter.

  3. Statement describing future research interests (3 page limit).

  4. 3 Letters of reference to be uploaded on AJO by referee, with at least one reference from outside LBNL/UC Berkeley.


The posting shall remain open until the position is filled, however for full consideration, please apply by close of business on January 31, 2019.



  • This is a full time, 2 years, 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 paid postdoctoral experience. Salary for Postdoctoral positions depends on years of experience post-degree.

  • Full-time, M-F, exempt (monthly paid) from overtime pay.

  • This position is represented by a union for collective bargaining purposes.

  • Salary will be predetermined based on postdoctoral step rates.

  • This position may be 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 will be primarily performed at Lawrence Berkeley National Lab, 1 Cyclotron Road, Berkeley, CA.


Berkeley Lab (LBNL) addresses the world’s most urgent scientific challenges by advancing sustainable energy, protecting human health, creating new materials, and revealing the origin and fate of the universe. Founded in 1931, Berkeley Lab’s scientific expertise has been recognized with 13 Nobel prizes. The University of California manages Berkeley Lab for the U.S. Department of Energy’s Office of Science.


Equal Employment Opportunity: Berkeley Lab is an Equal Opportunity/Affirmative Action Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, age, or protected veteran status. Berkeley Lab is in compliance with the Pay Transparency Nondiscrimination Provision under 41 CFR 60-1.4.  Click here to view the poster and supplement: "Equal Employment Opportunity is the Law."

Application Materials Required:
Submit the following items online at this website to complete your application:
And anything else requested in the position description.

Further Info:

© 2021 AcademicJobsOnline.Org. All Rights Reserved.