Maja Trebacz

Maja is a researcher at OpenAI, working on techniques for improving control and alignment as AI systems become more capable and agentic. Her team’s work combines longer-horizon research with hands-on deployment. They study long-term questions about how increasingly intelligent systems can be supervised, constrained, and corrected, while also building oversight systems that are used in practice today, both internally and externally (see recent work on code review and action monitoring for codex).