Nhan Tran

Scientist at Fermilab

Aurora, Illinois, United States
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

🤩
Rockstar
🎓
Top School
Nhan Tran is a physicist-turned-scientist with 13 years of experience at Fermilab, progressing from research associate to Wilson Fellow and now a Scientist working at the intersection of experimental physics and applied machine learning. He holds a Ph.D. in Physics from Johns Hopkins and a BA from Princeton, and applies deep domain knowledge to deploy ML models onto specialized hardware—contributing to open-source efforts like hls4ml to map neural networks to FPGAs. His work blends algorithm design, hardware-aware optimization (loop unrolling, array partitioning), and pipeline integration, enabling low-latency inference for physics instrumentation. Based in Aurora, Illinois, he brings both academic rigor and production-minded engineering to multidisciplinary teams, with a demonstrated knack for translating complex models into efficient edge-deployable implementations.
code13 years of coding experience
job6 years of employment as a software developer
bookJohns Hopkins University
bookBachelor of Arts - BA, Physics, Bachelor of Arts - BA, Physics at Princeton University
github-logo-circle

Github Skills (8)

neural-network10
fpga10
machine-learning10
python9
c-language8
cprogramming-language8
pytorch6
onnx6

Programming languages (11)

C#C++VHDLShellCSSSCSSObjective-CHTML

Github contributions (5)

github-logo-circle
fastmachinelearning/hls4ml

Oct 2017 - May 2022

Machine learning on FPGAs using HLS
Role in this project:
userML Engineer
Contributions:2 reviews, 159 commits, 47 PRs in 4 years 7 months
Contributions summary:Nhan contributed to the implementation of machine learning models on FPGAs. Their commits focused on defining and configuring neural network layers, including the addition of layer settings and unroll factors. They also modified the Keras-to-HLS conversion script, suggesting involvement in the model deployment pipeline. Furthermore, the user worked on optimizing the code for hardware, including loop unrolling and array partitioning.
pytorchpythonvivadofpgasonnx
nhanvtran/trackObservables

May 2016 - Mar 2019

Contributions:15 commits, 1 PR, 13 pushes in 2 years 10 months
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