Mark Stephenson
Principal Research Scientist at NVIDIA
Austin, Texas, United States
Summary
👤
Senior🎓
Top SchoolMark Stephenson is a Principal Research Scientist at NVIDIA with over a decade of experience applying compilers, architecture, and machine learning to optimize CUDA and graphics workloads. He holds a PhD from MIT where he led cross-disciplinary projects that used empirical performance data and learning techniques to automatically generate compiler and runtime optimizations. His career includes impactful systems work at IBM Research—writing a fault-resilient FFT library for PERCS and a Hadoop-based HTML parser for Power7 clusters—and early hardware design and VLSI experience from the University of Utah. Comfortable across Verilog, C, F#, Scala, and JavaScript, he blends low-level hardware insight with modern ML-driven tooling. Known for tackling both theory and production-scale engineering, he repeatedly bridges language/runtime research with practical, high-performance implementations. Based in Austin, he brings rare deep expertise in compiler analyses for heterogeneous compute and graphics platforms.
10 years of coding experience
9 years of employment as a software developer
Doctor of Philosophy (PhD) Computer Science, Doctor of Philosophy (PhD) Computer Science at Massachusetts Institute of TechnologyThe University of Utah
Github Skills (2)
instrumentation8
gpgpu7
Github contributions (1)
NVlabs/SASSI
Oct 2015 - Oct 2019
Contributions:6 releases, 8 commits, 2 PRs in 4 years
instrumentationgpgpuflexible
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.