The experimental high energy physics (HEP) group at the University of California San Diego (UCSD) invites applications from outstanding candidates for the position of postdoctoral researcher to work on the CMS experiment, real-time artificial intelligence (AI), and to apply findable, accessible, interoperable, and reusable (FAIR) principles to AI models and data in high energy physics.
The CMS group at UCSD is involved in developing novel geometric deep learning algorithms, including graph neural networks, for event reconstruction, anomaly detection, simulation, and ultrafast applications in field-programmable gate arrays (FPGAs) for the Level-1 trigger. Our group is also leading searches for exotic long-lived particles and measurements of Lorentz-boosted Higgs boson decays using machine learning (ML). The successful candidate will have the opportunity to join and lead these efforts.
As part of the FAIR4HEP project (https://fair4hep.github.io/), the successful candidate will also lead the curation of data sources from HEP, development of software frameworks to automatically train, evaluate, and compare benchmark AI models for a variety of HEP tasks, and publish sharable AI models and data following FAIR principles.
Ambitious applicants from diverse backgrounds are encouraged to apply.
A Ph.D. in physics is required. Prior experience in software development, FPGA firmware design or high-level synthesis, and ML is advantageous, but not essential. Completed applications should be sent to duarte-pd-recruit@physics.ucsd.edu and must include
The deadline for the receipt of the application is September 8, 2021, but the search will continue until the position is filled.
Our research group is committed to creating an antiracist, inclusive, and supportive workspace. UCSD is an equal opportunity/affirmative action employer with a strong institutional commitment to excellence through diversity.
FAIR4HEP is a collaboration between scientists at the University of Illinois at Urbana-Champaign, Massachusetts Institute of Technology, University of California at San Diego and the University of Minnesota
This research is supported by DE-SC0021258, DE-SC0021395, DE-SC0021225, and DE-SC0021396 from the Office of Advanced Scientific Computing Research within U.S. Department of Energy Office of Science.
