Projects
I lead the Interfaces research programme at ML@CL, focusing on interpretable, self-sustaining multi-agent AI systems.
The programme takes a systems perspective on the AI adoption problem: software systems are the interface between socio-technical needs and AI capabilities. It addresses the data dichotomy (data-driven systems must expose data that traditional architectures hide) and intellectual debt in deployed ML systems. Two complementary research lines: DOCS (data-oriented architectures) and S4 (self-sustaining systems with humans in control) support objectives to design, architect, and build AI-based systems and to interpret their autonomous behaviour. Work is validated across different domains, including critical ones like healthcare.
Prior to this, I worked as a postdoc on the AutoAI project.
Public software
Observable multi-agent systems
Semi-automatic literature survey tool for reproducible systematic reviews
Edge service placement simulation (with Joseph Poon, SEAMS 2026 artifact)
Student projects
Part III and Masters project topics at Cambridge are listed in the ML@CL project catalogue.