Mikita Balesni is an ML researcher and engineer with nine years of experience focused on empirical LLM safety and evaluating dangerous model capabilities. Currently a Member of Technical Staff at OpenAI, he previously co-founded Apollo Research to collaborate with frontier labs and governments on mitigating catastrophic AI risks. His background blends hands-on applied ML—improving news classification and publishing a NeurIPS '22 ML4AD first-author paper—with rigorous safety work at Stanford's Existential Risks Initiative. Comfortable moving between research and engineering, he has experience building production web applications, instrumenting interpretability analyses, and diagnosing large-scale dataset issues. Based in London, he combines multidisciplinary academic training in computer science and cybersecurity with a practical track record of turning alignment research into actionable evaluations.
9 years of coding experience
7 years of employment as a software developer
Master of Science - MS, Computer Science, Master of Science - MS, Computer Science at University of Tartu Institute of Computer Science
Exchange Semester, Exchange Semester at Mississippi College
Bachelor's degree, Cybersecurity, Bachelor's degree, Cybersecurity at Taras Shevchenko National University of Kyiv
Contributions:150 commits, 2 PRs, 109 pushes in 2 months
usabilityapipythonsurface
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
Mikita Balesni - Member Of Technical Staff at OpenAI