Jared Joselowitz is a Senior AI Research Engineer focused on AI alignment, interpretability, and evaluation. His Master’s research at Imperial College London explored inverse reinforcement learning to extract reward models from large language models, contributing to AI safety.With a background in Electrical Engineering and experience as a Data Scientist, Jared bridges the gap between theoretical AI research and real-world applications.
Outside of work, he enjoys watching and playing all kinds of sports, as well as movies and reading.