Renato Golin
Principal AI Software Research at Intel Labs
Cambridge, England, United Kingdom
Summary
🤩
Rockstar🎓
Top SchoolRenato Golin is a Principal AI Software Researcher based in Cambridge with over 15 years driving compiler, ML and HPC toolchain innovation at organizations like Intel Labs and Microsoft. A decades-long open source advocate and LLVM/MLIR maintainer, he blends deep compiler internals (LLVM/MLIR, Triton) with practical ML-for-programmer-productivity work and multi-GPU/distributed workload engineering. Renato has led technical teams and critical infrastructure projects—improving reproducible test suites, ARM support in Clang, and build/testing pipelines for high-profile projects such as LLVM and Microsoft’s Confidential Consortium Framework. His background in physics, molecular biology and mathematics underpins a systems-thinking approach that connects research-grade compilers to production ML and HPC stacks. Colleagues know him for turning research into durable, community-centered solutions that prioritize long-term collaboration over quick fixes.
15 years of coding experience
25 years of employment as a software developer
Mathematics and Computer Science, Mathematics and Computer Science at The Open UniversityPhysics, Physics at USP - Universidade de São Paulo
English, Portuguese
Stackoverflow
11reputation
17kreached
1answer
0questions
Github Skills (48)
algorithm10
algorithms10
c-language10
tls1210
architecture10
compiler-development10
testing10
v810
bash10
c1110
development-tools10
mlr10
tls1310
data-structure10
c1710
Programming languages (15)
Github contributions (5)
llvm/llvm-test-suite
Mar 2013 - Sep 2017
Role in this project:
Back-end Developer
Back-end DeveloperContributions:3 reviews, 26 commits, 1 comment in 4 years 6 months
Contributions summary:Renato primarily focused on improving the stability and reproducibility of the test suite by addressing platform-specific variations. They made changes to ensure consistent output across different architectures, including ARM and x86_64. This involved implementing custom random number generators and modifying sort criteria in several benchmarks, specifically within the MiBench and Polybench test suites. Further contributions include fixing an issue in ClamAV and improving the handling of floating-point comparisons.
llvm/llvm-project
Jan 2019 - Jun 2026
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.
Role in this project:Back-end Developer
Back-end DeveloperContributions:305 reviews, 44 PRs, 66 pushes in 7 years 5 months
Contributions summary:Renato primarily contributes to the LLVM project, focusing on the MLIR (Multi-Level Intermediate Representation) dialect. Their work involves extending Linalg named operations by implementing new functions like reciprocal, round, sqrt, rsqrt, square, tanh, erf, min, max, and powf. They also worked on generalizing named ops, addressing type casts and broadcasting issues, and removing redundant operations related to matmul, demonstrating a deep understanding of the project's compiler infrastructure.
compilerllvmtoolchain
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.