Thierry Besson
Principal Engineer at Zero ASIC
Boston, Massachusetts, United States
Summary
👤
Senior🎓
Top SchoolThierry Besson is a principal engineer and software architect with 35 years of deep expertise in EDA, specializing in logic and HDL synthesis, P&R, STA, formal verification and QoR-driven optimizations. He combines a strong C/C++ UNIX/Linux systems background with core algorithm and data-structure mastery, driving both hands-on development and technical leadership across international teams. Thierry has led and managed synthesis teams and delivered patented innovations in LUT-based mapping and integrated synthesis/formal flows, with work showcased at DAC 2023. Currently at Zero ASIC after directing software and EDA synthesis for Rapid Silicon’s Raptor flow, he continues to blend algorithmic rigour with product-focused engineering. An active open-source contributor, he has extended the PyTorch Glow compiler back-end with loader and operator improvements, reflecting interest in ML compilers and hardware acceleration. His career bridges academia (PhD-level training at INP Grenoble and UC Berkeley) and production-grade EDA tooling, often surfacing subtle trade-offs between area, timing and power.
8 years of coding experience
30 years of employment as a software developer
Ph.D student at EECS department, UC Berkeley, CA, USA with Pr. R.K.Brayton, Ph.D student at EECS department, UC Berkeley, CA, USA with Pr. R.K.Brayton at University of California, BerkeleyIngénieur ENSIMAG, groupe ENSI (Ecoles Nationales Supérieures d'Ingénieurs), computer science (Software Engineering & Artificial Intelligence), Ingénieur ENSIMAG, groupe ENSI (Ecoles Nationales Supérieures d'Ingénieurs), computer science (Software Engineering & Artificial Intelligence) at National School of Computer Science and Applied Mathematics of GrenoblePh.D., Computer Science, Ph.D., Computer Science at INP Grenoble & UC Berkeley
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (6)
compiler-design10
c-language10
onnx10
cprogramming-language10
image-processing9
machine-learning9
Programming languages (4)
Github contributions (5)
pytorch/glow
Jun 2018 - May 2022
Compiler for Neural Network hardware accelerators
Role in this project:
Back-end Developer
Back-end DeveloperContributions:13 reviews, 71 commits, 43 PRs in 3 years 11 months
Contributions summary:Thierry primarily contributed to the `pytorch/glow` repository by implementing and modifying features within the image classification tools. These changes included adding new image normalization modes, modifying the image classifier script to align with different model types, and implementing improvements to the Reshape operator. Furthermore, the user added support for Min/Max, Sqrt/Reciprocal, and Cast operators to the model loader, which demonstrates a focus on expanding the capabilities of the compiler. The contributions suggest involvement in compiler functionality and optimization.
compilerhardwareneural-network
Cadence-TIP-AI/glow
Aug 2018 - Apr 2022
Compiler for Neural Network hardware accelerators
Contributions:115 pushes, 54 branches in 3 years 8 months
compilerhardwareneural-network
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.