Benjamin Thorne
Lead Software Engineer at Atomic Industries
San Francisco, California, United States
Summary
👤
Senior🎓
Top SchoolBenjamin Thorne is a Lead Software Engineer in San Francisco with 10 years of experience at the intersection of simulation, optimization, and machine learning. Trained as an astrophysicist (PhD, Oxford), he transitioned from academic research roles at Princeton, Tokyo, and UC Davis into applied ML and engineering positions at Berkeley Lab and Atomic Industries. He builds production-ready systems that blend scientific rigor with software engineering best practices, moving models from experimental prototypes to scalable deployment. His background as a physicist gives him an uncommon strength in principled modeling and numerical simulation, enabling robust solutions for complex inverse and optimization problems. As a hands-on leader, he has progressed from machine learning engineer to lead engineer within Atomic Industries, mentoring teams while driving technical direction. He pairs deep research experience with practical engineering, making him adept at translating novel algorithms into reliable products.
10 years of coding experience
6 years of employment as a software developer
Doctor of Philosophy - PhD Astrophysics, Doctor of Philosophy - PhD Astrophysics at University of Oxford
Github Skills (27)
polarization10
cosmology10
simulations10
sky10
healpy10
simulation9
python9
mpi9
bayesian9
orbit9
julia8
gift8
automatic-differentiation8
physics8
gpu7
Programming languages (7)
Github contributions (5)
b-thorne/PySM_public
Aug 2016 - Nov 2019
PySM: Software for simulating the Galactic microwave sky
Contributions:1 release, 19 PRs, 103 pushes in 3 years 3 months
sentinel-1pythongalacticskyorbit
b-thorne/DustVAEder
Feb 2021 - Oct 2023
Set of variational autoencoder models to be used in the analysis of Galactic foregrounds to CMB experiments.
Contributions:4 PRs, 14 pushes, 1 branch in 2 years 8 months
variational-autoencoderastrophysicscosmologygenerative-model
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.