PeopleofSuperintelligence

Builder

Cody Hao Yu

Also known as Cody Yu

Cody Hao Yu helps make large language models easier to serve through vLLM and its PagedAttention memory system. He earned computer-science degrees at National Tsing Hua University in 2011 and 2013, then completed a UCLA PhD in 2019. At AWS AI, he researched Apache TVM and machine-learning systems from 2019 to April 2023. His work includes the Bring Your Own Codegen compiler framework, SGLang, and engineering roles at BosonAI and Anyscale. Since April 2025, he has been a Member of Technical Staff at OpenAI and has contributed to the GPT-5 System Card released alongside the model in August 2025.

Now at
OpenAI
Works
40
Badges

Publication numbers from OpenAlex, as of 19 October 2026. Citations and h-index are hidden because this OpenAlex record may be incomplete or mix in other authors.

Timeline

  1. 2011–2019

    Degrees in computer science

    He earns B.S. and M.S. degrees in computer science at National Tsing Hua University in 2011 and 2013, then completes a PhD at UCLA in 2019.

  2. 2019–April 2023

    Compiler research at AWS

    He joins AWS AI as an applied scientist in 2019 and researches Apache TVM and machine-learning systems.

  3. 2021

    Bring Your Own Codegen

    He coauthors Bring Your Own Codegen to Deep Learning Compiler in 2021, proposing an open-source framework that reuses compiler components and enables custom code generation.

  4. June 2023

    PagedAttention and vLLM

    He helps build vLLM, an open-source LLM serving engine built around PagedAttention; in 2023, the FastChat-vLLM backend serves Vicuna to millions of Chatbot Arena users.

  5. December 2023

    SGLang for language programs

    In December 2023, he coauthors SGLang, a system with a frontend language and runtime for executing complex language-model programs.

  6. 2024

    Tech lead at Anyscale

    In 2024, he serves as a staff software engineer and tech lead at Anyscale, optimizing LLM inference after serving as a founding engineer at BosonAI.

  7. Since April 2025

    OpenAI post-training work

    He joins OpenAI as a Member of Technical Staff in April 2025 and contributes to its GPT-5 System Card, published alongside the model's August 2025 launch.

Career

  1. Since 2025OpenAIMember of Technical Staff
  2. From 2024AnyscaleStaff software engineer and tech lead
  3. 2019–2023AmazonApplied scientist
  4. BosonAIFounding engineer

Education

  1. 2019University of California, Los AngelesPhD
  2. 2013National Tsing Hua UniversityB.S. and M.S. in computer science

From the biography.

  1. Language and speech leads the latest AI doctorate cohortIncludes Cody Hao Yu. We estimate how career areas differ across doctorate cohorts, which areas gained share, and how often a company role began soon after graduation.
  2. 13 of 79 people shaping AI with a former OpenAI role now work at AnthropicIncludes OpenAI. Our estimates of where OpenAI recruits came from and where people with former OpenAI roles work now.
  3. The median h-index is 53 at universities and 19 at frontier AI labsIncludes OpenAI. The median h-index is 53 at universities and 19 at frontier AI labs. We compare publishing careers, citations and moves to estimate how universities and frontier labs contribute to AI research.
  4. Google alumni founded or led 87 other organizations, the most among the labs we compareIncludes OpenAI. We trace 212 organizations founded or led by AI lab alumni, and 223 career moves between the labs.

Colleagues

People with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Cody Hao Yu yet. Send us a free-licensed photo.

  1. (Cody) Hao Yu | VAST lab vast.cs.ucla.edu. Checked 19 October 2026.
  2. Cody (Hao) Yu | alphaXiv alphaxiv.org. Checked 19 October 2026.
  3. [2105.03215] Bring Your Own Codegen to Deep Learning Compiler arxiv.org. Checked 19 October 2026.
  4. vLLM: Easy, Fast, and Cheap LLM Serving with PagedAttention | vLLM Blog vllm-project.github.io. Checked 19 October 2026.
  5. [2309.06180] Efficient Memory Management for Large Language Model Serving with PagedAttention arxiv.org. Checked 19 October 2026.
  6. [2312.07104] SGLang: Efficient Execution of Structured Language Model Programs arxiv.org. Checked 19 October 2026.
  7. Cody Yu | QCon San Francisco 2024 qconsf.com. Checked 19 October 2026.
  8. [2601.03267] OpenAI GPT-5 System Card arxiv.org. Checked 19 October 2026.