Carleton SCS: CRC in AI (multi-agent RL safety)
A single Canada Research Chair rather than a lab or centre. Carleton's own School of Computer Science profile lists "AI Safety" sixth among seven research interests ("Multi-agent Systems, Reinforcement Learning, Game Theory, Deep Learning, Machine Learning, AI Safety, Generative AI") and frames the work as solving "the problems of scale, non-stationarity, effective communication, safety, and sample inefficiency in multi-agent learning systems". The chairholder's own site advertises "one opening for a Postdoctoral Fellow for research that intersects the areas of multi-agent systems, AI safety, and reinforcement learning". The published output is multi-agent RL generally; the safety-labelled strands are inverse constrained RL and LLM-agent evaluation.