About the role
The team develops frameworks for detecting and mitigating misuse of AI systems for cyberattacks. The role involves managing a team to implement these strategies and collaborating with other departments on policy and tooling. This work ensures users can safely interact with the company's products.
Our summary of the posting; the original is on the Anthropic careers page.
What the posting requires
- Required
- SQL
- Python
- Data analysis
- Threat detection
- Cybersecurity
- Offensive techniques
- Exploit development
- Malware analysis
- Vulnerability research
- Bachelor's degree
- Preferred
- Large language models
- Product policy implementation
- LLM
- Content moderation
- AI misuse
- Policy at scale
These tags are our reading of the posting. They can miss something; the original posting is the reference.