PeopleofSuperintelligence

Researcher

Amir-Hossein Karimi

Also known as Amir H. Karimi

Amir-Hossein Karimi is a University of Waterloo AI researcher whose work links algorithmic recourse, causal inference and explainable AI with trustworthy human-AI systems. His experience spans technology and research roles at BlackBerry, Meta, Google Brain and DeepMind; he co-founded Brizi and earned computer science degrees at Waterloo and ETH Zurich. His research includes 2020 methods for model-agnostic counterfactual explanations and probabilistic recourse, a 2022 survey of algorithmic recourse, and an ETH Medal-winning 2023 dissertation. Since September 2025, he holds Waterloo’s Val O’Donovan Chair in Trustworthy AI, leads the CHARM Lab, and serves as an assistant professor and Vector Institute Faculty Affiliate.

Works
36
Citations
2,112
h-index
8
Badges
Links
Google Scholar

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. 2013–2022

    Technology roles across four companies

    His experience spans technology and research roles at BlackBerry in 2013, Meta from 2014 to 2016, Google Brain in 2021, and Google DeepMind in 2022.

  2. 2015–2018

    Degrees at Toronto and Waterloo

    He earns a bachelor's degree in Engineering Science at the University of Toronto in 2015 and a Master of Mathematics in Computer Science at Waterloo in 2018.

  3. By 2018

    Cofounding Brizi

    After graduating from Toronto, he spends two years in industry and co-founds Brizi, one of the teams selected for Canada’s Next 36 Entrepreneurship Institute. In 2018, he receives the University of Waterloo Alumni Gold Medal.

  4. 2020

    Counterfactual explanations and recourse

    At AISTATS in 2020, he and coauthors propose a model-agnostic counterfactual explanation algorithm using formal verification and satisfiability solving. At NeurIPS 2020, he coauthors a probabilistic approach for choosing recourse actions under limited causal knowledge.

  5. 2022

    A survey of algorithmic recourse

    He coauthors a survey of algorithmic recourse in ACM Computing Surveys in 2022.

  6. 2023

    An ETH Medal

    He completes a PhD in Computer Science at ETH Zurich in 2023 and receives the ETH Medal for a dissertation on algorithmic recourse, causal consistency, fairness and robustness. Prof. Bernhard Schölkopf supervises the dissertation at the Max Planck Institute for Intelligent Systems.

  7. 2024

    A teaching excellence award

    In 2024, he receives the Igor Ivkovic Teaching Excellence Award at the University of Waterloo.

  8. Since September 2025

    Chair in Trustworthy AI

    He takes up the Val O’Donovan Chair in Trustworthy AI at Waterloo in September 2025. As of October 2026, he is an Assistant Professor in Waterloo’s Department of Electrical and Computer Engineering and a Vector Institute Faculty Affiliate, and leads the CHARM Lab. The lab explores causal inference, explainable AI and program synthesis, with a mission to advance trustworthy human-AI symbiosis.

Career

  1. Since 2025University of WaterlooVal O’Donovan Chair in Trustworthy AI
  2. Since 2025Vector InstituteFaculty Affiliate
  3. From 2022Google DeepMind
  4. From 2021Google Brain
  5. 2020–2022University of California, Irvine
  6. 2020–2024Max Planck Institute for Intelligent Systems
  7. 2014–2016Meta
  8. 2013Blackberry
  9. BriziCo-founder

Education

  1. 2023ETH ZurichPhD in Computer Science
  2. 2018University of WaterlooMaster of Mathematics in Computer Science
  3. 2015University of TorontoBachelor's degree in Engineering Science

From the biography and OpenAlex affiliations (the years of papers that list the organization), so some years are approximate.

  1. Of 943 people shaping AI who worked at Google, 446 work there nowIncludes Amir-Hossein Karimi. 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.
  2. The median h-index is 48 at universities and 14 at frontier AI labsIncludes Amir-Hossein Karimi. 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.
  3. Nonprofit roles are 2.3 times as common in AI safetyIncludes Vector Institute. We estimate where people focused on safety, alignment and evaluation work. Nonprofit roles appear for 25.1% of safety people with known affiliations, compared with 11.0% in other areas.
  4. Universities (31%) and startups and other companies (25%) employ the largest shares of 2020–2026 entrantsIncludes Vector Institute. 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.

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 Amir-Hossein Karimi yet. Send us a free-licensed photo.

  1. Amir H. Karimi | Home amirhkarimi.com. Checked 20 October 2026.
  2. Amir-Hossein Karimi | Electrical and Computer Engineering | University of Waterloo uwaterloo.ca. Checked 20 October 2026.
  3. Computer science student Amir-Hossein Karimi wins prestigious Alumni Gold Medal | Cheriton School of Computer Science | University of Waterloo cs.uwaterloo.ca. Checked 20 October 2026.
  4. Model-Agnostic Counterfactual Explanations for Consequential Decisions proceedings.mlr.press. Checked 20 October 2026.
  5. Algorithmic recourse under imperfect causal knowledge: a probabilistic approach papers.nips.cc. Checked 20 October 2026.
  6. Five doctoral graduates receive ETH Medals – Department of Computer Science | ETH Zurich inf.ethz.ch. Checked 20 October 2026.
  7. Research chairs, awards and honours | Electrical and Computer Engineering | University of Waterloo uwaterloo.ca. Checked 20 October 2026.
  8. Amir-Hossein Karimi - Vector Institute for Artificial Intelligence vectorinstitute.ai. Checked 20 October 2026.