Toryn Klassen is a postdoctoral fellow working with Sheila McIlraith. He completed his Ph.D. in Computer Science at the University of Toronto. He has researched a number of topics in artificial intelligence, often involving some combination of logic, modelling beliefs, and reinforcement learning. In the area of AI safety, his research has included work on evaluating fairness over time and on the problem of avoiding side effects from incomplete objective specifications.