About the role
The Safeguards organization develops systems to ensure AI models are safe and beneficial. This role manages a research engineering team focused on biological safety, which includes creating evaluations, datasets, and classifiers to govern how models handle biological knowledge. The manager guides technical direction, oversees team projects, and ensures the quality of safety measures.
Our summary of the posting; the original is on the Anthropic careers page.
What the posting requires
- Required
- Python
- Scientific programming
- Data analysis
- ML fundamentals
- Modern biology
- Dual-use research
- Evaluation design
- Measurement
- Biosecurity frameworks
- Classifier development
- Preferred
- Adversarial robustness
- Red-teaming
- Safety evaluation
- ML systems
- People management
Preferred experience: 8+ yrs
These tags are our reading of the posting. They can miss something; the original posting is the reference.