Chief Scientist at Asymmetric Security, building the future of cyberdefense and incident response.
Previously, Director of Software Engineering at Salesforce, leading RL post-training for GUI agents in Agentforce — via the Convergence acquisition, where I was a founding team member building frontier browser agents. Before that, Research Scientist at Spotify, and PhD at the University of Cambridge in collaboration with Microsoft Research.
I am interested in developing safe and effective machine learning systems that can successfully complete complex tasks in the real world. My work has often explored (inverse) reinforcement learning, imitation learning and simulation in order to learn from intrinsic rewards and humans, applied most recently to large language/multimodal models for autonomous computer-using agents — and now to AI for cyberdefense and incident response.
Recent News
- Apr 2026
Joined Asymmetric Security as Chief Scientist to build the future of cyberdefense and incident response.Asymmetric Security
- May 2025
We're being acquired by Salesforce! I'll be joining as a Director of Software Engineering to continue our work building the future of computer-using agents.Announcement
- Dec 2024
Our first agent Proxy has achieved state-of-the-art results (82%) on the WebVoyager benchmark!Post
- Sep 2024
Joined Convergence Labs Ltd. as a Member of Technical Staff! We're a seed-stage startup building a future of abundance by automating workflows with AI.Convergence
- Sep 2024
New work accepted to NeurIPS 2024: "Discovering Preference Optimization Algorithms with and for Large Language Models"!Paper
- May 2024
"Dense Reward for Free in Reinforcement Learning from Human Feedback" accepted to ICML!Paper