About the role
The team evaluates AI models to determine if they can be manipulated to generate harmful cyberattack materials. The role involves simulating attacker behaviors and crafting adversarial prompts to uncover vulnerabilities in the models' safety measures.
Our summary of the posting; the original is on the Handshake careers page.
What the posting requires
- Required
- Python
- Exploitability assessment
- PowerShell
- Technical output evaluation
- Bash
- C
- C++
- JavaScript
- Code evaluation
- MITRE ATT&CK
- Preferred
- Security clearance
- LLM APIs
- Evaluation tooling
- Cloud security
- AI security
- Trust and safety
These tags are our reading of the posting. They can miss something; the original posting is the reference.