PeopleofSuperintelligence

Builder

Omar Khattab

Omar Khattab is a computer scientist behind ColBERT, a late-interaction retrieval model, and DSPy, a programming model for language-model pipelines. He earned a computer science degree at Carnegie Mellon University in Qatar in 2019 and completed a Stanford PhD in January 2025 under Christopher Potts and Matei Zaharia. With Zaharia, he introduced ColBERT in 2020; he was first author of the DSPy paper in October 2023 and coauthored GEPA and Recursive Language Models in 2025. Databricks employed him as a research scientist from June 2024 to June 2025, and the WARP retrieval engine he coauthored won a Best Paper Award at SIGIR 2025. Since July 2025, he is an assistant professor at MIT EECS and a member of CSAIL, where he leads the OASYS lab.

Now at
MIT CSAIL
Works
88
Badges
Links
Website, Google Scholar, X and GitHub

Publication numbers from OpenAlex, as of 22 October 2026. Citations and h-index are hidden because this OpenAlex record may be incomplete or mix in other authors.

Timeline

  1. 2019

    Carnegie Mellon Qatar degree

    He earns a computer science degree from Carnegie Mellon University in Qatar in 2019 and goes on to a computer science PhD at Stanford.

  2. 2020

    ColBERT and late interaction

    With Matei Zaharia, he introduces ColBERT in 2020, a ranking model that encodes the query and the document separately with BERT and then compares them in a cheap late interaction step. Document representations can be computed offline, which speeds up query processing considerably.

  3. October 2023

    The DSPy programming model

    In October 2023, he is first author of the DSPy paper, with coauthors that include Matei Zaharia and Christopher Potts. DSPy is a programming model that abstracts language-model pipelines as text transformation graphs, with a compiler that optimizes any pipeline to maximize a given metric.

  4. February 2024

    Compound AI systems post

    In February 2024, he is one of eleven authors of the Berkeley AI Research blog post 'The Shift from Models to Compound AI Systems', alongside Matei Zaharia, Ali Ghodsi and others. The post argues that state-of-the-art AI results increasingly come from compound systems with multiple components.

  5. June 2024–June 2025

    Research scientist at Databricks

    He works as a research scientist at Databricks from June 2024 to June 2025. In January 2025, he completes his Stanford PhD under Christopher Potts and Matei Zaharia.

  6. 2025

    A SIGIR best paper award

    WARP, a multi-vector retrieval engine he coauthors with Jan Luca Scheerer, Matei Zaharia, Christopher Potts and Gustavo Alonso, cuts end-to-end latency by 41 times against the reference implementation of XTR. The paper wins a Best Paper Award at SIGIR 2025.

  7. 2025

    GEPA and Recursive Language Models

    In July 2025, he coauthors GEPA, a prompt optimizer that learns from natural-language reflection; across six tasks it outperforms GRPO by 6% on average while using up to 35 times fewer rollouts. In December 2025, he coauthors Recursive Language Models with Alex L. Zhang and Tim Kraska, an inference paradigm in which a model recursively calls itself over snippets of a long prompt.

  8. Since July 2025

    Assistant professor at MIT

    He joins MIT in July 2025 as an assistant professor in the Department of Electrical Engineering and Computer Science, holds the TIBCO Founders Career Development Professorship, is a member of CSAIL, and leads the OASYS lab, short for Open Source AI Systems. By August 2026, DSPy has been downloaded over 55 million times.

Career

  1. Since 2025Massachusetts Institute of TechnologyAssistant Professor
  2. Since 2025MIT CSAILMember
  3. 2024–2025DatabricksResearch Scientist

Education

  1. 2025Stanford UniversityPhD
  2. 2019Carnegie Mellon University QatarComputer science degree

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 Omar Khattab. 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. 23% of people shaping AI who left a university for a company later returned to a universityIncludes Omar Khattab. We estimate that 468 of the 2,011 people shaping AI who left a university for a company (23%) later returned to a university after a median of 5 years, and 163 of 829 (20%) made the reverse round trip.
  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 Omar Khattab yet. Send us a free-licensed photo.

  1. Omar Khattab: Bio, Work & Ideas | AI Engineer ai.engineer. Checked 20 October 2026.
  2. MIT Schwarzman College of Computing welcomes 11 new faculty for 2025 | MIT News news.mit.edu. Checked 20 October 2026.
  3. ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT arxiv.org. Checked 20 October 2026.
  4. DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines arxiv.org. Checked 20 October 2026.
  5. The Shift from Models to Compound AI Systems – The Berkeley Artificial Intelligence Research Blog bair.berkeley.edu. Checked 20 October 2026.
  6. Solving AI’s ‘Last Mile’ Problem - MIT EECS eecs.mit.edu. Checked 20 October 2026.
  7. WARP: An Efficient Engine for Multi-Vector Retrieval arxiv.org. Checked 20 October 2026.
  8. Omar Khattab omarkhattab.com. Checked 20 October 2026.
  9. Omar Khattab, Co-Principal Investigator - MIT Environmental Research + Action eralabs.mit.edu. Checked 20 October 2026.
  10. GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning arxiv.org. Checked 20 October 2026.
  11. Recursive Language Models arxiv.org. Checked 20 October 2026.
  12. School of Engineering welcomes new faculty in 2024-25 | MIT News news.mit.edu. Checked 20 October 2026.