Ryan Lundqvist

Ryan grew up in Northern Virginia and completed his undergrad in CS at Georgia Tech a year ago, where he was part of GT AISI. After graduating he worked at Meta before leaving to join the fellowship. He has also researched evaluation awareness and mechanistic interpretability under Santiago Aranguri at Goodfire, during SPAR, and is broadly interested in situational awareness, interpretability, mitigating existential risks, and alignment science.