Researcher, Frontier Risk Mitigations
OpenAI · San Francisco · London, UK
CHECKED 1H AGO
Frontier labonsite$380k–$500k
At a glance
Highlights
- Develop novel safety mitigations for frontier AI agents that plan and act.
- Build evaluations to assess emerging misuse and misalignment risks.
- Define future safe AI systems and shape industry best practices.
What they offer
- equity
Ideal candidate
Mission-driven AI safety researcher excited by long-term AGI safety who thrives hands-on with large-scale systems and cross-functional collaboration across security and science domains.
Requirements
- 2+ years of experience in AI safety, especially RLHF, human-AI collaboration, interpretability, or control
- PhD or degree in computer science, machine learning, or related field
- 4+ years of research engineering experience with proficiency in Python or similar languages
- Experience working with large-scale AI systems
- Deep enthusiasm for long-term AI safety and technical paths to safe AGI
- Willing to apply methods from interpretability, robustness, alignment, and control
Lab profile
About OpenAI
Builds safe frontier AI models and products like ChatGPT for broad benefit.
What they build
- ChatGPT
- OpenAI API
- Frontier AI models
Known for
- Frontier-scale distributed ML training
- Massive GPU fleet and data center operations
- Exabyte-scale data lakes and streaming
- AI alignment and safety research
Key facts
- Operates one of the world's largest GPU fleets