OpenAI Researcher Announces Hiring for Misalignment Safety Team
Micah Carroll shares that the recursive self-improvement preparedness subteam seeks researchers for monitoring and misalignment work.
Micah Carroll posted that his OpenAI subteam focused on recursive self-improvement and misalignment preparedness is hiring researchers. The roles center on monitoring, misalignment assessments, monitorability, third-party auditing, and external risk communication. A linked OpenAI careers page lists an open full-time position for Researcher, Recursive Self-Improvement Safety Preparedness in San Francisco. Mark Chen, OpenAI's chief research officer, separately posted that many strong researchers are choosing alignment work and that the lab is still hiring. Colleagues including Ethan Perez, Tomek Korbak, and Kai Chen replied with endorsements of the team and the opportunity.
We are hiring! This may be the best time ever to join: we are incredibly bandwidth bottlenecked and there is a lot of support for almost any impactful misalignment work you can think of. I think we also have a pretty good epistemic environment and a very fun team Topics:…
Reactions from ranked influencers
13 postsThese are incredibly misleading headlines – @OpenAI Preparedness is very much alive and well by any meaningful definition Our subteam – RSI/misalignment Preparedness – is doing more urgent work than ever, and has never been more empowered to do so!
OpenAI has quietly disbanded its catastrophic risk team (preparedness) “It is kind of scary; there is an urgency now to get this right,” one person close to OpenAI said. Another said there was a “burbling sense of responsibility and dread that they aren’t on the ball enough”.…
METR* and Redwood! ❤️
@MicahCarroll is one of the sharpest people I’ve ever worked with (and there are a lot of sharp people at OpenAI). His team is doing critical research on monitoring and loss-of-control risks in an era of rapidly advancing capabilities. Consider joining.
We are hiring! This may be the best time ever to join: we are incredibly bandwidth bottlenecked and there is a lot of support for almost any impactful misalignment work you can think of. I think we also have a pretty good epistemic environment and a very fun team Topics:…
@kaicathyc And I’m definitely not the sharpest person on the team! The real pitch is getting to work with people like @Marcus_J_W @tomekkorbak @phuguo @eeeeiluj and everyone else who joined more recently!
work with Micah!
We are hiring! This may be the best time ever to join: we are incredibly bandwidth bottlenecked and there is a lot of support for almost any impactful misalignment work you can think of. I think we also have a pretty good epistemic environment and a very fun team Topics:…
These days opportunities for impact are served on a silver platter, joining our team is one of them:
We are hiring! This may be the best time ever to join: we are incredibly bandwidth bottlenecked and there is a lot of support for almost any impactful misalignment work you can think of. I think we also have a pretty good epistemic environment and a very fun team Topics:…