Joshua Vita

Sr. Computational Materials Scientist

Tucson, Arizona, 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

👤
Senior
🎓
Top School
Joshua Vita is a Sr. Computational Materials Scientist with nine years of experience building production-ready ML systems that accelerate scientific discovery, currently applying that expertise at Elemynt after a postdoc at Lawrence Livermore National Laboratory. He designs scalable training and inference pipelines for HPC environments, led multi-institution teams to deploy cluster-based Bayesian optimization and ensemble uncertainty frameworks that produced large accuracy and speed gains, and has deep experience integrating Python ML stacks with high-performance C++ simulation codes. Joshua has a strong track record building large scientific data infrastructure—e.g., ColabFit, which hosts billions of training points and tens of thousands of downloads—and routinely bridges research and engineering to deliver reproducible, deployable tools. Based in Tucson, AZ, he combines domain knowledge in materials science with practical software engineering and open collaboration to turn complex physical problems into robust, auditable ML workflows.
code9 years of coding experience
job11 years of employment as a software developer
bookThe University of Arizona
bookDoctor of Philosophy - PhD, Materials Science, Doctor of Philosophy - PhD, Materials Science at University of Illinois Urbana-Champaign
github-logo-circle

Github Skills (33)

docking10
lammps9
javascript9
simulation9
materials-informatics9
datasets9
open-source9
databases7
rest7
rest-api7
database6
react6
snakemake6
lda5
python5

Programming languages (6)

C#C++MakefileHTMLJupyter NotebookPython

Github contributions (5)

github-logo-circle
TrinkleGroup/svreg

Sep 2020 - Jun 2021

A package for constructing interatomic potentials using symbolic regression with "structure vectors" (svreg = Structure Vector REGression).
Contributions:2 PRs, 174 pushes, 32 branches in 8 months
regressioninteratomic-potentialsvectorssymbolic-regressionmachine-learning
TrinkleGroup/s-meam

Apr 2018 - Nov 2020

Contributions:365 pushes, 57 branches, 2 issues in 2 years 7 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