Dr. Amir-Hossein Karimi is an award-winning researcher and educator, and an Assistant Professor in the Department of Electrical and Computer Engineering and the Cheriton School of Computer Science (cross-appointed) at the University of Waterloo, and a Vector Institute Faculty Affiliate. He leads the Collaborative Human-AI Reasoning Machines (✨CHARM✨) Lab, dedicated to advancing safe and trustworthy human-AI collaborations.
Dr. Karimi's scholarly contributions have been showcased almost exclusively at top-tier AI and ML venues including NeurIPS, ICML, COLM, AAAI, AISTATS, ACM FAccT, and ACM AIES, as well as Nature Scientific Reports. He has authored influential publications such as a comprehensive survey paper in the prestigious ACM Computing Surveys and Trends in Cognitive Sciences, holds a patent, and is a contributing author of a book chapter. Dr. Karimi’s work on algorithmic recourse has notably elevated its prominence in responsible AI research, with its presence growing from almost none to hundreds on Google Scholar in just five years; algorithmic recourse is now a mandatory criterion in key sectors, including Canada’s Treasury Board Directive on Automated Decision-Making, and Dr. Karimi has advocated for meaningful recourse in testimony to Canada’s House of Commons. Several of Dr. Karimi's papers have received over 100 citations each. Dedicated to knowledge mobilization and reproducibility, his open-source code has garnered over 100 GitHub stars. To learn more about algorithmic recourse, visit this website.
Dr. Karimi enjoys teaching diverse audiences, from broad topics in AI for the public, to courses on ML for students, to AI strategy for leaders, to specialized tutorials for scholars. In his first teaching term at the University of Waterloo, he was honored with the 2024 Igor Ivkovic Teaching Excellence Award. Dr. Karimi has been invited to present talks, lectures, and tutorials at institutions such as MIT, Harvard, ETH Zurich, MILA, University College London, Cyber Valley Health, Institute of Mathematical Statistics, NEC Europe Labs, Google DeepMind, and Google Brain. He gave notable tutorials at KDD 2023 (on Causal Explainable AI) and at the Toronto ML Summit 2024 (on Algorithmic Recourse).
Prior to joining Waterloo, Dr. Karimi accumulated over 15 years of experience in leading technology and research roles at BlackBerry (2013), Meta (Facebook) (2014–2016), Google Brain (2021), and Google DeepMind (2022), and has consulted for startups and incubators including NEXT AI. His contributions have earned him multiple accolades, such as the UofToronto Spirit of Engineering Science Award (2015), the UWaterloo Alumni Gold Medal Award (2018), the NSERC Canada Graduate Scholarship - Doctorate (2018), the Google PhD Fellowship (2021), the ETH Zurich Medal (2024), the NSERC Discovery Grants & Supplements (2024), the Igor Ivkovic Teaching Excellence Award (2024), and the O'Donovan Chair in Trustworthy AI (2025). To view the full CV, click here.
As AI systems become increasingly embedded in high-stakes domains such as healthcare, education, finance, and transportation, ensuring their reliability, transparency, and adaptability is critical.
The vision of the Collaborative Human-AI Reasoning Machines (✨CHARM✨) Lab is to enable trustworthy human-AI ecosystems, where AI systems can be understood, influenced, and improved over time.
Our mission is to develop principled methods for trustworthy human-AI systems with three core capabilities:
Our work draws on tools from causal reasoning, explainable AI, neuro-symbolic learning, and human-AI interaction, and spans disciplines including cognitive science, social sciences, and multi-agent systems.
The lab is always on the lookout for exceptional and highly motivated students/visitors across all levels (bachelor's, master's, doctoral, postdoctoral). Our research sits at the intersection of theory and practice, focusing on foundational questions motivated by real-world impact. If this direction resonates with your interests and background in machine learning, computer science, or related fields, please fill out fill out this form.
Dr. Karimi sees research and teaching as two sides of the same coin. Research at the frontier gives him something worth teaching: new ideas become tutorials and advanced courses, and in time the foundations taught to everyone. Teaching, in turn, sharpens the research: explaining an idea to a student, an executive, or a policymaker reveals what is truly understood and what is not.
Each circle is an audience this work reaches; hover or tap one to see its work.
Dr. Karimi is grateful for the generous funding support from the University of Waterloo, NSERC, CIFAR, Google, Waterloo.AI, and the O'Donovan Family, enabling his team to push the boundaries of human-AI research.
Besides academic contributions, Dr. Karimi also consults internationally for several startups, leveraging his expertise for discovery, product-market fit, and scaling of operations, in addition to fundraising and grant writing. He is available to discuss how his research and experience can deliver value to your organization and stakeholders.
For consultations, press inquiries, or teaching engagements at your organization or event, reach out via email.