Tim Besard - Software Engineer at JuliaHub

Tim Besard

Software Engineer at JuliaHub

Ghent, East Flanders, Belgium

Join Prog.AI to see contacts

Summary

🤩

Rockstar

🎓

Top School

Tim Besard is a software engineer with 16 years of experience specializing in compiler technology and GPU back-ends, currently working at Julia Computing on the CUDA backend for the Julia language. His PhD work and a visiting stint at MIT focused on compiling high-level languages for GPUs, blending language design with practical compiler optimizations. He is a prolific open-source contributor to flagship projects like LLVM and Julia itself, adding low-level C APIs and CUDA integrations that bridge compiler internals to GPU runtimes. Tim’s work spans from embedded PCIe tooling to high-performance ML stacks (Flux.jl and CUDA.jl), reflecting a rare mix of systems-level rigor and numerical computing pragmatism. Based in Ghent, he combines academic depth with production-grade engineering, often surfacing subtle compatibility and performance fixes that enable GPU features to work reliably across platforms.

16 years of coding experience

Doctor of Philosophy - PhD, Computer Science Engineering, Doctor of Philosophy - PhD, Computer Science Engineering at Universiteit Gent

Master of Science - MS, Applied Computer Science Engineering, Master of Science - MS, Applied Computer Science Engineering at Hogeschool Gent (HoGent)

Dutch, English, French

Stackoverflow

Stats

109reputation

4kreached

4answers

1question

Github Skills (43)

c-language10

artificial-neural-networks10

dma10

llvm10

gpu-programming10

machine-learning10

capi10

c1110

c1710

calculus10

automatic-differentiation10

deeplearning-ai10

low-level-programming10

code-generation10

compiler-design10

Programming languages (21)

C++CRustCMakeGoPerlHTMLJupyter Notebook

Github contributions (5)

JuliaGPU/CUDA.jl

Oct 2019 - Jan 2023

CUDA programming in Julia.

Role in this project:

Back-end Developer

Contributions:2 releases, 471 reviews, 2379 commits in 3 years 3 months

Contributions summary:Tim primarily worked on the low-level implementation of CUDA GPU acceleration within the Julia programming language. Their contributions focused on developing and optimizing the `cuda.jl` package, involving tasks such as implementing wrappers for CUDA libraries (like cuBLAS), fixing potential issues, and adding functionalities for numerical computations. They also were involved in enhancing library support by working on the library and integration tests.

cudagpucuda-programmingjulia

JuliaLang/julia

May 2013 - Jan 2023

The Julia Programming Language

Role in this project:

Back-end Developer & Compiler Engineer

Contributions:177 reviews, 527 commits, 507 PRs in 9 years 10 months

Contributions summary:Tim primarily contributed to the Julia Programming Language's core functionality, focusing on the compiler and low-level aspects. Their commits added support for building with ccache, extended the `:meta` expression for saving extra information, and implemented improvements to the llvmcall and multiversioning functionalities. They also improved the support for Windows builds by patching the compiler.

sciencejulia-languagemachine-learningjulialangpetsc

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.

Request Free Trial