PeopleofSuperintelligence

Builder

Ying Sheng

Also known as 盛颖

Ying Sheng builds open systems for running large language models and evaluating their outputs. She earned computer science degrees at Shanghai Jiao Tong University and Columbia and a PhD at Stanford, then worked on AI for Code at X and LLM serving at UC Berkeley. Her projects include vLLM, FlexGen, SGLang, Chatbot Arena and S-LoRA, and she co-founded RadixArk, the company behind SGLang. She is an assistant professor of computer science at UCLA, where she works on efficient LLMs and automated reasoning.

Badges
Links
Website, Google Scholar and GitHub

Timeline

  1. 2016–2017

    Computer science degrees

    She earns a B.E. in computer science and technology at Shanghai Jiao Tong University in 2016 and an M.S. in computer science at Columbia University in 2017.

  2. 2022

    AI for Code at X

    At X’s Moonshot Factory in 2022, she works on AI for Code with Michele Catasta as a PhD resident.

  3. 2023–2024

    Research at UC Berkeley

    She visits Sky at UC Berkeley from 2023 to 2024, working with Ion Stoica and Joseph E. Gonzalez.

  4. 2023

    vLLM and FlexGen

    In 2023, she coauthors the vLLM paper, which introduces an open-source library for fast LLM inference and serving. She also coauthors FlexGen, a high-throughput engine for running LLMs with limited GPU memory.

  5. 2023

    SGLang and Rising Stars

    In 2023, she coauthors SGLang, a system for executing structured language-model programs that uses RadixAttention for KV-cache reuse. MLCommons names her among its 2023 Rising Stars, a cohort of researchers at the intersection of machine learning and systems.

  6. 2024

    Fairness and LLM systems

    At Stanford, she is a PhD student in computer science advised by Clark Barrett when she presents a fairness scheduler for LLM serving on June 5, 2024. The Virtual Token Counter uses continuous batching to allocate service fairly. In 2024, she coauthors the Chatbot Arena paper on human-preference evaluation and S-LoRA, which scales serving to thousands of adapters across GPUs.

  7. October 2024–January 2026

    From xAI to RadixArk

    From October 2024 to August 2025, she works as a member of technical staff at xAI and co-leads its inference team. By January 2026, she becomes the co-founder and CEO of RadixArk, the company behind SGLang.

  8. July 2026

    Assistant professor at UCLA

    In July 2026, she joins UCLA Samueli as an assistant professor of computer science. She holds a Stanford PhD and focuses on efficient LLMs and automated reasoning models. She also serves as a co-founder and director of LMSYS.org.

Career

  1. From 2026RadixArkCo-founder and CEO
  2. From 2026University of California, Los AngelesAssistant Professor of Computer Science
  3. 2024–2025xAIMember of Technical Staff; Co-lead of Inference Team
  4. 2023–2024University of California, Berkeley
  5. 2022Moonshot FactoryPhD Resident
  6. LMSYS OrgCo-founder and Director

Education

  1. 2017Columbia UniversityM.S. in Computer Science
  2. 2016Shanghai Jiao Tong UniversityB.E. in Computer Science and Technology
  3. Stanford UniversityPhD

From the biography.

  1. The median h-index is 48 at universities and 14 at frontier AI labsIncludes Ying Sheng. The median h-index is 48 at universities and 14 at frontier AI labs. We compare publishing careers, recent citations, dual appointments and job moves across 2,420 university researchers and 308 frontier-lab researchers.
  2. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes University of California, Los Angeles. 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.
  3. Universities keep AI researchers for a median of 6 years, compared with 2 years at frontier labsIncludes University of California, Los Angeles. Across 15,811 dated work stays (6,529 people), median role tenure runs from 6 years at universities to 2 years at frontier labs. We compare all five organization types, starting decades from the 1970s to the 2020s, and the organizations that keep people longest.
  4. People shaping AI work at a median of 3 organizations over a career: 3 for university starters and institute and lab starters, versus 2 for company startersIncludes University of California, Los Angeles. Across 6,853 people shaping AI with a dated work role, we estimate a median of 3 parent organizations over a career (mean 3.6), comparing role groups, starting sectors and starting decades from the 1950s to 2020–2026.

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 Ying Sheng yet. Send us a free-licensed photo.

  1. Ying Sheng sites.google.com. Checked 21 October 2026.
  2. vLLM: Easy, Fast, and Cheap LLM Serving with PagedAttention vllm-project.github.io. Checked 21 October 2026.
  3. FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU arxiv.org. Checked 21 October 2026.
  4. SGLang: Efficient Execution of Structured Language Model Programs arxiv.org. Checked 21 October 2026.
  5. Introducing the 2023 MLCommons Rising Stars mlcommons.netlify.app. Checked 21 October 2026.
  6. Fairness in Serving Large Language Models aha.stanford.edu. Checked 21 October 2026.
  7. Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference arxiv.org. Checked 21 October 2026.
  8. SLoRA: Scalable Serving of Thousands of LoRA Adapters proceedings.mlsys.org. Checked 21 October 2026.
  9. Sources: Project SGLang spins out as RadixArk with $400M valuation as inference market explodes techcrunch.com. Checked 21 October 2026.
  10. UCLA Computer Science Welcomes Six Faculty Members cs.ucla.edu. Checked 21 October 2026.
  11. New Faculty 2024–2025 | UCLA Samueli School of Engineering samueli.ucla.edu. Checked 21 October 2026.