Matthew Bachstein
HPC Systems Architect at University of Tennessee, Knoxville
Knoxville, Tennessee, United States
Summary
👤
Senior🎓
Top SchoolMatthew Bachstein is an HPC Systems Architect and Computer Science PhD candidate with a decade of experience building and operating high-performance, heterogeneous compute environments. His work blends applied mathematics and optimization with practical systems engineering—specializing in GPU auto-tuning (CUDA and some OpenCL) and MPI at scale—where he treats kernel configuration as an optimization problem that also produces rich datasets for statistical analysis. Over a progressive career at the University of Tennessee he has moved from hands-on support and graduate research into system administration, archival storage, and now architectural leadership for campus HPC. He brings a rare combination of algorithmic thinking, data-science curiosity, and DevOps-focused infrastructure design, enabling reproducible tuning pipelines and scalable storage solutions. Based in Knoxville, he pairs deep academic rigor with production experience tuning and administering large heterogeneous clusters.
10 years of coding experience
8 years of employment as a software developer
Bachelor of Science Cum Laude Mathematical Sciences, Bachelor of Science Cum Laude Mathematical Sciences at Clemson UniversityDoctor of Philosophy (Ph.D.) Computer Science, Doctor of Philosophy (Ph.D.) Computer Science at University of Tennessee, Knoxville
English, German
Github Skills (15)
evaluation7
filesystem6
lifecycle6
parallel-processing3
computational-science2
distributed-computing2
openmp2
cluster-computing2
parallel2
infiniband2
mpi1
hpc1
scalability1
parallel-computing1
high-performance1
Programming languages (3)
Github contributions (5)
olcf/lcio
May 2018 - Aug 2018
Lifecycle based file system I/O evaluation tools
Contributions:75 commits, 3 PRs, 2 pushes in 3 months
file-basedlifecycleevaluationfile-system-basedfilesystem
mjbach/pcircle
Jul 2018 - Jan 2022
A suite of parallel file system tools designed for performance and scalability
Contributions:5 pushes in 3 years 5 months
multithreadingsystem-toolsinfinibandparallelportability
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.