PeopleofSuperintelligence

Researcher

Jonathan Ragan-Kelley

Jonathan Ragan-Kelley is a computer scientist at MIT whose programming languages and compilers help image-processing and AI programs run efficiently on modern hardware. After degrees at Stanford and MIT, he completed his PhD in 2014 after co-creating the Halide language with Andrew Adams, and he held posts at Stanford, Google and Berkeley before joining MIT in January 2020. He coauthored the NeurIPS 2022 Outstanding Paper "Gradient Descent: The Ultimate Optimizer," received the ACM SIGGRAPH Significant New Researcher Award in 2021, and became a Sloan Research Fellow in 2023. In 2025, his group introduced the Exo 2 scheduling language, and he co-advised PASTA, a CSAIL and Google method that trains LLMs to decode independent chunks of text in parallel. He is an associate professor with tenure in MIT's Department of Electrical Engineering and Computer Science, a role he has held since July 2025.

Now at
MIT CSAIL
Badges

Timeline

  1. 2004–2014

    Degrees at Stanford and MIT

    He earns a BS in computer science at Stanford in 2004, then a master's degree in 2007 and a PhD in 2014 at MIT. His doctoral advisors are Frédo Durand and Saman Amarasinghe.

  2. 2012–2013

    Co-creating the Halide language

    During his MIT PhD, he designs the Halide image-processing language with Andrew Adams; MIT announces it in 2012 and releases it in 2013. Halide becomes the industry standard for image processing and is used in Google phones and Adobe Photoshop. His earlier Lightspeed system is used to produce movies at Industrial Light and Magic for several years and is a finalist for a technical Oscar award.

  3. 2014–2019

    Stanford postdoc, then Berkeley

    He works as a postdoc with Pat Hanrahan at Stanford from 2014 to 2016, then as a visiting researcher at Google from 2016 to 2017. From 2017 to 2019, he is an assistant professor in UC Berkeley's EECS department, where he develops a graduate class on compilers.

  4. 2020–2021

    MIT faculty and a SIGGRAPH award

    He joins MIT in January 2020. In 2021, he receives ACM SIGGRAPH's Significant New Researcher Award for outstanding contributions to systems and compilers in rendering and computational photography.

  5. 2022

    A NeurIPS Outstanding Paper

    He coauthors "Gradient Descent: The Ultimate Optimizer" with Kartik Chandra, Audrey Xie and Erik Meijer, which receives an Outstanding Paper award at NeurIPS 2022. The paper shows how to compute hypergradients automatically with a simple modification to backpropagation, and applies the method recursively to hyper-hyperparameters.

  6. 2023

    Sloan Fellowship and PLDI award

    He is named a Sloan Research Fellow in 2023, and his original 2013 Halide paper receives the PLDI Test of Time Award. The EECS department also gives him its Outstanding Educator Award in 2023.

  7. 2024–2025

    Exo 2 and faster LLM inference

    In 2024, he works with the MIT-IBM Watson AI Lab on Exo, a language developed in his group that gives engineers control over how the compiler maps programs to hardware, and on changes to transformer-based LLMs that let them run more efficiently on AI hardware. In March 2025, Exo 2 from his CSAIL group lets users define new scheduling operations outside the compiler and can reduce total schedule code by a factor of 100. In 2025, he co-advises PASTA with Michael Carbin, a CSAIL and Google method that trains LLMs to decode independent chunks of text in parallel and reaches geometric mean speedups of nearly 2x on AlpacaEval.

  8. Since July 2025

    Tenured associate professor at MIT

    He becomes an associate professor with tenure in MIT's Department of Electrical Engineering and Computer Science in July 2025. He is a principal investigator with CSAIL, and developers at Apple and Intel use his Exo compiler.

Career

  1. Since 2020Massachusetts Institute of TechnologyAssociate professor with tenure
  2. NowMIT CSAILPrincipal investigator
  3. 2017–2019University of California, BerkeleyAssistant professor
  4. 2016–2017GoogleVisiting researcher
  5. 2014–2016Stanford UniversityPostdoc

Education

  1. 2014Massachusetts Institute of TechnologyPhD
  2. 2007Massachusetts Institute of TechnologyMaster's degree
  3. 2004Stanford UniversityBS in computer science

From the biography.

  1. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Jonathan Ragan-Kelley. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  2. Of 943 people shaping AI who worked at Google, 446 work there nowIncludes Jonathan Ragan-Kelley. Our estimates of where the 943 people shaping AI who worked at Google and Google DeepMind work now: 446 at Google and 452 across 278 other organizations.
  3. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Massachusetts Institute of Technology. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.
  4. Google had the most people shaping AI every year from 2014 to 2025Includes Massachusetts Institute of Technology. Our estimates of which organizations employed the most people shaping AI each year from 1955 to 2025, tracing the shift from university labs to companies.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Jonathan Ragan-Kelley yet. Send us a free-licensed photo.

  1. Ragan-Kelley named ACM SIGGRAPH's 2021 Significant New Researcher | MIT CSAIL csail.mit.edu. Checked 21 October 2026.
  2. Jonathan Ragan-Kelley | EECS at UC Berkeley www2.eecs.berkeley.edu. Checked 21 October 2026.
  3. Jonathan Ragan-Kelley people.csail.mit.edu. Checked 21 October 2026.
  4. Halide (programming language) - Wikipedia en.wikipedia.org. Checked 21 October 2026.
  5. Department of EECS Announces Promotions - MIT EECS eecs.mit.edu. Checked 21 October 2026.
  6. Jonathan Ragan-Kelley wins ACM SIGGRAPH 2021 Significant New Researcher Award - EECS at Berkeley eecs.berkeley.edu. Checked 21 October 2026.
  7. NeurIPS 2022 Awards neurips.cc. Checked 21 October 2026.
  8. CSAIL's Ragan-Kelley named 2023 Sloan Research Fellow | MIT CSAIL csail.mit.edu. Checked 21 October 2026.
  9. Creating bespoke programming languages for efficient visual AI systems | MIT News news.mit.edu. Checked 21 October 2026.
  10. High-performance computing, with much less code | MIT News news.mit.edu. Checked 21 October 2026.
  11. Speeding up LLM inference with parallelism | MIT CSAIL csail.mit.edu. Checked 21 October 2026.
  12. The tenured engineers of 2025 | MIT News news.mit.edu. Checked 21 October 2026.
  13. Jonathan Ragan-Kelley | MIT-IBM Computing Research Lab mitibm.mit.edu. Checked 21 October 2026.