Brian Decost
Materials Scientist
Gaithersburg, Maryland, United States
Summary
👤
Senior🎓
Top SchoolBrian Decost is a computational materials scientist with 11 years of experience applying machine learning to guide physical and computational experiments for alloy design and microstructure characterization. Based at NIST after postdoctoral work at Carnegie Mellon, he blends deep academic training (PhD/MS in Materials Science) with hands-on research to translate data-driven models into experimentally actionable insights. He focuses on integrating ML orchestration with microscopy and materials processing, accelerating materials discovery and characterization cycles. Known for bridging theory and practice, he cultivates reproducible workflows and open, shareable tools (see bdecost.github.io) that make complex materials data more usable for experimentalists.
11 years of coding experience
3 years of employment as a software developer
Doctor of Philosophy (PhD), Materials Science and Engineering, Doctor of Philosophy (PhD), Materials Science and Engineering at Carnegie Mellon UniversityBachelor of Science (B.S.), Chemical Engineering, Bachelor of Science (B.S.), Chemical Engineering at University of Florida
English, Spanish, Portuguese
Github Skills (35)
graph10
google-scholar10
graph-embedding10
pytorch-geometric10
graph-neural-network10
dft9
geometric-deep-learning9
materials-informatics9
image-data9
gaussian9
quantum-computing8
stochastic-processes8
lammps8
gaussian-processes8
neural-network8
Programming languages (3)
Github contributions (5)
bdecost/uhcsdb
Dec 2016 - Oct 2021
Contributions:67 commits, 23 pushes, 1 branch in 4 years 10 months
bdecost/spparks-demo
Jul 2014 - Jul 2014
Contributions:42 commits in 7 days
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.