About
I am Professor of Safe Artificial Intelligence in the Department of Computing at Imperial College London, where I lead the Safe AI Lab, and co-founder and CTO of Safe Intelligence. My research is aimed at developing rigorous methods for making artificial intelligence systems verifiable.
Since 2000 I have worked on the formal verification of autonomous and multi-agent systems, including pioneering work on model checking multi-agent systems and, from 2015, on the formal verification of machine-learning systems. My work has addressed temporal, epistemic and strategic properties of autonomous systems, parameterised systems such as swarms, neural networks and learning-enabled agents. My current research focuses on scalable robustness verification for large vision and multimodal models, autonomous AI agents, and neuro-symbolic systems.
Appointments
2011–present — Professor of Safe Artificial Intelligence, Imperial College London
2008–2011 — Reader, Imperial College London
2006–2008 — Senior Lecturer, Imperial College London
2004–2006 — Senior Lecturer, University College London
2002–2004 — Lecturer, King’s College London
2000–2002 — Research Fellow, Imperial College London
Selected distinctions
Fellow of EurAI (2017)
Royal Academy of Engineering Chair in Emerging Technologies (2018–2028)
EPSRC Leadership Fellowship (2010–2016)
ACM Distinguished Member (2020)
Selected Imperial roles
Enterprise Champion, Department of Computing — current
Founding Co-Director and Imperial Lead, UKRI Centre for Doctoral Training in Safe and Trusted Artificial Intelligence — 2019–2024
Director of Strategy, Department of Computing — 2015–2020
Deputy Head of Department, Department of Computing — 2016–2017
Contact
Department of Computing
Imperial College London
I read every enquiry, although I am unable to reply to all messages individually.