I am a Principal Research Data Scientist at iSpot, where I work on generative AI, agentic LLM systems, and multimodal AI for advertising intelligence and enterprise analytics workflows.
My recent work has focused on the development of iSpot SAGE AI, an enterprise AI platform for multimodal creative analysis and advertising intelligence. I have worked across the full lifecycle of these systems, from early research and prototyping through productionization and operational handoff, with a focus on multimodal reasoning, cognitive modeling, and scalable AI workflows built on proprietary enterprise-scale datasets.
I received my Ph.D. in Mathematics from the University of Illinois Chicago in 2021 under the supervision of Alex Furman. My mathematical research focused on dynamical systems, ergodic theory, probability, and hyperbolic geometry, spanning both theoretical and computational problems. Across both mathematics and AI, I am broadly interested in complex systems, representation, optimization, and the interaction between abstract structure and large-scale computation.
You can find my publications here, or explore the Packing Problems and Complex Dynamics sections.
Professional inquiries: robert [dot] kozma [at] ispot [dot] tv
Academic correspondence: robert [at] kozma [dot] ai
GitHub: github.com/rkthijs