Javier Duarte - Associate Professor Of Physics

Javier Duarte

Associate Professor Of Physics

San Diego, California, United States

Join Prog.AI to see contacts

Summary

🤩

Rockstar

🎓

Top School

Javier Duarte is an associate professor of physics at UC San Diego who blends frontier particle physics with cutting‑edge machine learning to improve measurements of the Higgs boson and to hunt for new physics at the CERN LHC. With 11 years of experience spanning Caltech, Fermilab, and UCSD, he leads a team developing AI techniques and hardware‑accelerated ML—work recognized by a Sloan Fellowship, DOE Early Career Award, and leadership in an NSF institute for accelerated AI algorithms. He is a hands‑on developer in major open‑source efforts, contributing to CMS offline software (cmssw) and the hls4ml project that brings neural networks to FPGAs, reflecting a rare mix of experimental detector expertise and production ML engineering. Based in San Diego, he combines deep theoretical training (PhD Caltech) with practical code contributions that bridge analysis algorithms and accelerator-friendly implementations.

11 years of coding experience

4 years of employment as a software developer

Bachelor of Science - BS, Physics and Mathematics, Bachelor of Science - BS, Physics and Mathematics at Massachusetts Institute of Technology

California Institute of Technology

English, Spanish

Github Skills (12)

fpga10

cms10

hlsl10

c-language10

high-energy-physics10

offline-web-app10

cpp10

cprogramming-language10

cplus10

offline-app10

machine-learning9

keras9

Programming languages (17)

C#C++CCMakeTeXJSONHTMLJupyter Notebook

Github contributions (5)

fastmachinelearning/hls4ml

Dec 2017 - Jan 2023

Machine learning on FPGAs using HLS

Role in this project:

ML Engineer

Contributions:4 releases, 140 reviews, 219 commits in 5 years 2 months

Contributions summary:Javier contributed to the implementation of 1D convolution functionality and the integration of a test project within the `hls4ml` repository. Their work included the creation of a `nnet_conv.h` file that defined the structure and functions for performing 1D convolutions, including configuration parameters and buffer management. Further, they added a test project and test files to validate this implementation.

pytorchpythonvivadofpgasonnx

cms-sw/cmssw

Mar 2018 - Nov 2020

CMS Offline Software

Role in this project:

Back-end Developer

Contributions:20 reviews, 85 commits, 22 PRs in 2 years 8 months

Contributions summary:Javier primarily contributed to the implementation of the Higgs Interaction Net tagger within the CMS offline software project. They introduced and modified code related to feature extraction for charged particles and secondary vertices, specifically integrating features like `cpf_ptrel`, `sv_ptrel` and related calculations. They also appear to have been refactoring and debugging code to address compile warnings. Furthermore, the user integrated the use of the DeepBoostedJet producers and updated the configuration to accommodate these changes.

cmscernweb-appc-plus-plusbackbonejs

Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.

Request Free Trial