Job description
OpenAI • San Francisco, CA
San Francisco Bay Area
$295,000 - $445,000
- In this role, you'll design and execute cutting-edge attacks and adversarial evaluations to uncover how AI safety measures fail.
- Develop worst-case demonstrations that make AGI alignment risks concrete for stakeholders.
- Create automated tools and infrastructure to scale red-teaming and stress testing.
- Conduct research on alignment technique failures and propose improvements.
- Publish influential papers and partner with cross-functional teams on safety integration.
OpenAI is a frontier AI research and product company, with teams working on alignment, policy, and security. You can read concerns about doing harm by working at a frontier AI company in our career review on the topic, including concerns about OpenAI in particular.
Our Take On This Role: We have concerns about OpenAI's track record on safety and responsible development and do not recommend almost any roles at OpenAI. Nonetheless, it is possible that OpenAI will create AGI in the next decade, in which case safety and security work at the company could be extremely important. If you receive a job offer from OpenAI, consider contacting us for career advice.