Lilian Weng
Lilian Weng
Organization
OpenAI
Position
Head of Safety Systems
Intelligence Briefing
Official OpenAI safety committee materials list Weng as Head of Safety Systems. She is one of the best-known internal leaders on OpenAI's model safety, evaluation, and system-level risk mitigation efforts.
Operational History
Promoted to Head of Safety Systems
Elevated to lead the Safety Systems team at OpenAI.
careerJoined OpenAI
Became a Research Scientist at OpenAI, focusing on safety and alignment.
careerAGI Position Assessment
Unknown
OpenAI's public materials place her at the core of technical safety systems work.
OpenAI's public materials place her at the core of technical safety systems work.
Intercepted Communications
“Safety is not just a feature; it's a fundamental aspect of AI development.”
“Alignment challenges are at the forefront of our research agenda.”
“We must ensure that AI systems are robust and reliable.”
“Evaluating AI systems requires a multi-faceted approach.”
“Our goal is to mitigate risks associated with advanced AI technologies.”
Known Associates
Sam Altman
colleagueCEO of OpenAI, collaborates closely with Weng on safety initiatives.
View Dossier →Dario Amodei
colleagueFormer VP of Research at OpenAI, worked with Weng on alignment projects.
View Dossier →Mira Murati
colleagueCTO of OpenAI, collaborates with Weng on technical safety strategies.
View Dossier →Ilya Sutskever
mentorCo-founder and Chief Scientist of OpenAI, provides guidance on research directions.
View Dossier →Organizational Affiliations
Current
OpenAI
Head of Safety Systems
2023-present
Former
OpenAI
Research Scientist
2021-2023
Dossier last updated: 2026-03-04