Jonathan Ragan-kelley
Associate Professor
Cambridge, Massachusetts, United States
Summary
🤩
Rockstar🎓
Top SchoolJonathan Ragan-Kelley is an Associate Professor of Computer Science at MIT with 18 years of experience bridging academic research and systems-level engineering. He specializes in compilers and high-performance data-parallel computation, contributing to the widely used Halide project where he improved back-end code generation, added an OpenCL backend, and optimized memory and expression analyses. His career spans top institutions—MIT, Berkeley, and Stanford—and industry research stints at NVIDIA, Intel, and Adobe, reflecting deep GPU and graphics expertise dating back to early R&D roles in visual effects. Jonathan combines rigorous PhD-level research with practical compiler engineering, frequently turning theory into performant, portable implementations. Colleagues know him for refactoring complex compiler architectures to boost real-world performance while keeping projects accessible to both researchers and practitioners.
18 years of coding experience
14 years of employment as a software developer
PhD Electrical Engineering & Computer Science, PhD Electrical Engineering & Computer Science at Massachusetts Institute of TechnologyBS Computer Science, BS Computer Science at Stanford University
Github Skills (6)
compiler-design10
c-language10
cprogramming-language10
optimization10
computer-engineering9
opencl9
Programming languages (16)
Github contributions (5)
halide/Halide
Dec 2010 - Aug 2020
a language for fast, portable data-parallel computation
Role in this project:
Back-end Developer & Compiler Engineer
Back-end Developer & Compiler EngineerContributions:773 commits, 3 PRs, 26 pushes in 9 years 10 months
Contributions summary:Jonathan's contributions primarily involved modifications and enhancements to the Halide compiler, focusing on improving its capabilities and performance. Their work included bug fixes for Darwin builds and FImage tests, enhancements to the code generation process, refactoring of the compiler architecture, and improvements to the analysis of expressions for optimization. Their contributions included the addition of a new OpenCL backend and contributions to memory management, illustrating their focus on compiler development and performance.
computationhexagonhalideparallelgpu
halide/homebrew-halide
Jul 2015 - Jan 2018
Homebrew recipe for Halide binary distribution
Contributions:6 commits, 2 PRs, 5 pushes in 2 years 7 months
recipehomebrewdistributionhalide
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.