Alexander Turner is an independent researcher and PhD-trained AI scientist based in Berkeley with a decade of experience bridging theoretical foundations and hands-on agent development. His work spans academic and applied settings—from postdoctoral research and collaborations at CHAI and Oxford’s FHI to mentoring junior alignment researchers at SERI—focusing on agent behavior, retargetability, and incentives like deactivation avoidance. He has built planning-agent libraries, novel environments (including a ground-up chess environment), and has practical experience steering language models via activation vectors. Comfortable both teaching and mentoring, he has a track record of translating formal theorems into testable experiments and tooling. Known for tinkering roots in game-driven CS, he combines curiosity about video-game-inspired problems with rigorous safety-oriented research.
10 years of coding experience
4 years of employment as a software developer
Bachelor's degree, Bachelor's degree at Grinnell College
Doctor of Philosophy - PhD, Doctor of Philosophy - PhD at Oregon State University
Tools for running experiments on RL agents in procgen environments
Contributions:356 commits, 184 pushes, 10 branches in 1 month
deep-learningmazemlopenai-gymprocgen
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.
Request Free Trial
Alexander Turner - Independent Researcher at Self-employed