Khashayar Ghamati

I’m Khashayar -- an AI engineer working on systems that keep learning after they’re deployed.

I’m currently Principal AI Engineer at Inframatic Engineering, where I lead the design and delivery of adaptive AI for compliance automation in critical infrastructure: knowledge-graph retrieval, multi-agent architectures, and computer vision, built to run in production rather than in a notebook. Behind that sits more than a decade of Python and software engineering, and a habit of taking research-grade ideas -- online learning, reinforcement learning, continual and meta-learning -- and making them reliable enough to ship.

That engineering practice is grounded in published work. I defended my doctoral thesis at the University of Hertfordshire’s Robotics Research Group in June 2026, on NOVA, a framework for novelty detection and continual learning in human–robot interaction, validated on the ARI humanoid platform. I continue to hold an academic appointment there, supervising BSc and MSc students. My work appears in IEEE TCDS, RO-MAN, ICSR and Sensors, alongside an Alan Turing Institute output; I review for IEEE TCDS and co-organised the SS03 workshop at ICSR 2026.

If you’d like to get in touch about research collaboration, speaking, or anything at the intersection of adaptive AI and real-world systems -- say hello.