Mark Gottscho
Member Of Technical Staff at OpenAI
Mountain View, California, United States
Summary
👤
Senior🎓
Top SchoolMark Gottscho is a Member of Technical Staff at OpenAI with 13 years of experience bridging hardware and software for large-scale AI systems. He previously led compiler and hardware co‑design at SambaNova—founding and managing an Operators Team and formalizing ISA/assembly for next‑gen RDUs—and spent five years at Google driving TPU architecture, RTL, and verified design libraries used in production at massive scale. Comfortable across Rust, SystemVerilog, Python, and C++, Mark combines deep microarchitectural expertise (memory systems, interconnects, mixed precision kernels) with compiler work (MLIR dialects, PJRT plugins) to deliver full‑stack AI accelerators. He holds a PhD from UCLA and has a track record of building teams, improving engineering processes, and shipping silicon features that accelerate vision and inference workloads. An interesting throughline: he repeatedly marries docs-as-code and formalization practices to improve HW/SW collaboration and developer productivity.
13 years of coding experience
15 years of employment as a software developer
University of California, Los Angeles
English
Github Skills (23)
verilog10
hardware10
converting9
benchmark9
asciidoctor9
benchmarking9
extensible9
docbook8
pipeline8
asciidoc8
converter8
synthesis7
manpage7
scalable7
html6
Programming languages (6)
Github contributions (5)
nanocad-lab/X-Mem
Jun 2015 - May 2016
Contributions:28 commits, 57 pushes, 1 branch in 10 months
benchmarkmemorybenchmarkingextensible
xlsynth/bedrock-rtl
Sep 2024 - Apr 2025
High quality and composable RTL libraries in SystemVerilog
Contributions:540 reviews, 507 PRs, 610 pushes in 6 months
hardwarertlverilog
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.