About the role
The AI Model Policy team works with AI researchers to evaluate model behavior against customer policies. The trainer examines user requests and model responses, classifying them according to policy guidelines. This role involves nuanced judgment, precise reasoning, and clear communication to ensure consistent and accurate AI evaluations.
Our summary of the posting; the original is on the Handshake careers page.
What the posting requires
- Required
- Evaluate
- Distinguish
- Write
- Identify
- Calibration
- Apply policy
- Evaluation frameworks
- AI model
- Policy boundaries
- Rationales
- Preferred
- Long conversations
- Incomplete context
- Conflicting evidence
- AI safety
- Language models
- Rubrics
These tags are our reading of the posting. They can miss something; the original posting is the reference.