Ryan Greenblatt serves as the Chief Scientist at Redwood Research, where his work focuses on technical AI safety research. He is recognized as the lead author of the paper "Alignment faking in Large Language Models."

Prior to his current role, Greenblatt gained experience through various internships, including as a Software Engineer Intern at Optiver, a Quantitative Research Engineer Intern at Stevens Capital Management Lp, and a Robotics Software Engineer Internship at Locus Robotics.