PeopleofSuperintelligence

Researcher

Ian Arawjo

Ian Arawjo is a human-computer interaction researcher who studies programming, AI and the evaluation of large language models. A graduate of Concordia University in Montréal, he earned a PhD in information science at Cornell University under Tapan Parikh, with dissertation work on programming as a social and cultural practice. His papers won Best Paper Honorable Mentions at CSCW 2019, CHI 2020 and UIST 2022, and he invented notational programming, in which handwritten notation interoperates with typewritten code. As a postdoctoral fellow at Harvard University, he developed ChainForge, an open-source visual toolkit for prompt engineering and LLM hypothesis testing, and in 2024 he coauthored "Antagonistic AI" and the EvalGen paper "Who Validates the Validators?" He is an assistant professor at the Université de Montréal, where he founded and leads the Montréal HCI group and is an associate academic member of Mila.

Timeline

  1. 2014–2017

    Games for poetry and programming

    A graduate of Concordia University in Montréal with a degree in Computation Arts and Computer Science, he coauthors PoetryLab, a close listening game for iOS, at CHI PLAY in 2014. In 2017, he coauthors "Teaching Programming with Gamified Semantics" at CHI 2017.

  2. 2019–2020

    Cornell PhD and two honorable mentions

    He holds a PhD in information science from Cornell University, advised by Tapan Parikh, with dissertation work on programming as a social and cultural practice. His first-authored CSCW 2019 paper "Computing Education for Intercultural Learning" earns a Best Paper Honorable Mention. In 2020, his single-author CHI paper "To Write Code: The Cultural Fabrication of Programming Notation and Practice" earns the same award.

  3. 2022

    Notational programming and Notate

    In 2022, his paper "Notational Programming for Notebook Environments: A Case Study with Quantum Circuits" earns a Best Paper Honorable Mention at UIST 2022. It extends notational programming, his paradigm in which handwritten notation such as diagrams and writing interoperates with typewritten code. Notate, a publicly available Jupyter notebook extension, lets users insert drawing canvases into inline code.

  4. 2023–2024

    ChainForge at Harvard

    As a postdoctoral fellow at Harvard University, he works with Elena Glassman in the Harvard HCI group and develops ChainForge with Glassman, Priyan Vaithilingam and Martin Wattenberg. The paper "ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing" appears as a preprint in September 2023 and earns a Best Paper Honorable Mention at CHI 2024. ChainForge is an open-source toolkit with a graphical interface for comparing responses across models and prompt variations.

  5. 2024

    Antagonistic AI and EvalGen

    In February 2024, he coauthors "Antagonistic AI" with Alice Cai and Elena Glassman, which lays out a design space for AI systems that are disagreeable, rude, interrupting or confrontational. In April 2024, he coauthors "Who Validates the Validators?" with Shreya Shankar, J.D. Zamfirescu-Pereira, Björn Hartmann and Aditya Parameswaran, which presents the EvalGen interface for aligning LLM-generated evaluation functions with human requirements. The EvalGen paper appears at UIST 2024 and is cited as the chief motivation for new features in the LangSmith and Autoblocks LLMOps tools.

  6. 2025

    ChainBuddy and Semantic Commit

    In 2025, he publishes "ChainBuddy: An AI-assisted Agent System for Generating LLM Pipelines" at CHI 2025 with Jingyue Zhang. His UIST 2025 paper "Semantic Commit: Helping Users Update Intent Specifications for AI Memory at Scale" is presented in Busan, South Korea.

  7. As of October 2026

    Professor leading Montréal HCI

    He is an assistant professor of human-computer interaction at the Université de Montréal's Department of Computer Science and Operations Research, an associate academic member of Mila, and founder of the Montréal HCI group, which he leads with Damien Masson. He is the creator and lead developer of the open-source ChainForge and Splat tools, receives an FRQ New Investigator grant to study the management of intent specifications in human-AI interaction, and has two group papers at CHI 2026.

Career

  1. NowUniversité de MontréalAssistant Professor, Founder and Lead
  2. NowMilaAssociate Academic Member
  3. 2023–2024Harvard UniversityPostdoctoral Fellow

Education

  1. Concordia UniversityDegree in Computation Arts and Computer Science
  2. Cornell UniversityPhD

From the biography.

  1. The median h-index is 48 at universities and 14 at frontier AI labsIncludes Université de Montréal. 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. 20% of people at companies who shape AI also hold a university role, led by Google and Stanford UniversityIncludes Université de Montréal. We estimate that 539 of the 6,766 people with a known current organization (8%) hold both a university role and a company role, including 20% of people at companies and 13% of people at universities.
  3. Universities (31%) and startups and other companies (25%) employ the largest shares of 2020–2026 entrantsIncludes Mila. Among 819 people whose first recorded role started in 2020–2026 and who have a known current organization, 60% work in commercial sectors (25% at startups and other companies, 23% at frontier labs and 13% at big tech, with 9 in two), and 31% work at universities, compared with 66% for earlier entrants.
  4. Companies supply the most prior-work hires at 7 of the 9 frontier AI labsIncludes Mila. Our estimates of the organizations where 550 people worked directly before joining 9 frontier AI labs across 620 career transitions, comparing the main feeder organizations per lab.

Colleagues

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

Sources and credits

Photo: We have no published photo of Ian Arawjo yet. Send us a free-licensed photo.

  1. Ian Arawjo ianarawjo.com. Checked 21 October 2026.
  2. Ian Arawjo: Publications ianarawjo.com. Checked 21 October 2026.
  3. Ian Arawjo | Mila mila.quebec. Checked 21 October 2026.
  4. Ian Arawjo: Notational Programming ianarawjo.com. Checked 21 October 2026.
  5. ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing arxiv.org. Checked 21 October 2026.
  6. Antagonistic AI arxiv.org. Checked 21 October 2026.
  7. Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences arxiv.org. Checked 21 October 2026.
  8. Montréal HCI hci.iro.umontreal.ca. Checked 21 October 2026.