OPEN ROLE · /openai-researcher-recursive-self-improvement-safety
Researcher, Recursive Self-Improvement Safety
OOpenAISan Francisco · FullTime
ABOUT THIS ROLE
ABOUT THE TEAM Preparedness is a critical Safety Research team at OpenAI, which is focused on mitigating AI threats https://openai.com/index/updating-our-preparedness-framework/ that could scale to an extreme level of severity. Our work involves: - Tracking and prediction. Monitoring https://openai.com/index/how-we-monitor-internal-coding-agents-misalignment/ and predicting the evolving misalignment propensities and capabilities of frontier AI systems. - Mitigation. Keeping misuse safeguards, al… Full description ↗