What the posting requires
- Required
- Machine learning
- Model evaluations
- Evaluations
- Large language models
- Failure modes
- Safety signals
- Research problems
- Engineering ability
- Experiments
- Misalignment monitoring
- Preferred
- AI monitoring
- Automated evaluations
- Adversarial testing
- Model behavior analysis
- Interpretability
- Scalable oversight
These tags are our reading of the posting. They can miss something; the original posting is the reference.