Kyle Reynoso

Kyle is a Research Manager for the Singapore AI Safety Fellowship. He has a background in empirical alignment and interpretability research, alongside AI safety field-building in Southeast Asia. Previously, he taught two cohorts of WhiteBox Research interpretability upskilling program, was a research fellow at Pivotal and SPAR, and led program design for Condor Camp SEA. Concurrent with the fellowship, he delivers lectures for TARA's ARENA-based Singapore and Manila cohorts.