Jonathan Colen
Machine Learning Engineer at William & Mary
Summary
👤
SeniorJonathan Colen is a research-focused data scientist and Research Assistant Professor who builds interpretable AI models to connect machine learning with physical, environmental, and social systems. With nine years of experience spanning PhD-level research at the University of Chicago and hands-on projects at national labs, he has scaled pipelines for terabyte-scale microscopy and distilled neural networks into compact, physics-based equations that retain strong predictive power. He combines expertise in deep learning, dimensionality reduction, and sparse regression with production-oriented skills in HPC pipelines and automated training on Slurm clusters. Notably, he led a team that reduced a neural model by 100,000x in parameter count while preserving 77% accuracy, demonstrating a talent for turning complex models into interpretable, efficient tools. Based in Norfolk, VA, he blends academic rigor with applied problem-solving across health, environmental, and physical science domains.
9 years of coding experience
Github Skills (14)
gpu10
python10
numpy9
pint9
neural-network9
machine-learning9
deep-learning9
tensor8
autograd8
gpu-acceleration8
pulsar8
visualization4
tensorflow3
git3
Programming languages (3)
Github contributions (5)
jcolen/ML_ActiveNematics
Nov 2020 - Jan 2025
Code repository for ArXiv:2006:13203
Contributions:3 releases, 4 PRs, 6 pushes in 4 years 3 months
jcolen/kelvinmach
Jun 2018 - Dec 2020
Contributions:27 commits, 8 pushes in 2 years 5 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.