About the role
The Model Policy team establishes guidelines for the safe operation of advanced AI systems. This role involves assessing and mitigating dangers in models that process various types of media, creating rules and standards for their behavior. The work translates potential harms into concrete safety measures and collaborates with technical experts to implement these guidelines.
Our summary of the posting; the original is on the OpenAI careers page.
What the posting requires
- Required
- Policy design
- Harm theories
- Safety regressions
- Policy artifacts
- Audio
- Threat models
- Failure analysis
- Model training
- Image
- Safety policies
- Preferred
- Policy systems
- Technical judgment
- Technical fluency
- Model behavior testing
- AI tools
- Data analysis
These tags are our reading of the posting. They can miss something; the original posting is the reference.