Similar Jobs
See allForward Deployed Engineer, AI Trust and Reliability
Hopper
Global
Python
AI Safety
Security Engineering
Senior Security Researcher (Red Team)
Pindrop
US
Python
Penetration Testing
Cloud Security
Product Security Engineer
Emergence AI
US
Application Security
Threat Modeling
Kubernetes
Principal Attack Engineer
Horizon3
US
Python
Offensive Security
AI/LLM Security
Software Engineer, Cybersecurity Benchmarks
Epoch AI
Global
Software Engineering
Red Teaming
About the Role:
- Join an expert pool supporting AI safety testing projects.
- Lead evaluations across security, fairness, and domain-specific safety.
What You'll Do:
- Design and lead red teaming campaigns to identify attack vectors.
- Develop jailbreak techniques and document them for reproducibility.
- Test agent systems for prompt injection vulnerabilities.
What We're Looking For:
- At least five years of experience in security testing, trust and safety, or related domains.
- Experience designing test plans, threat models, or audits.
- Hands-on experience testing AI systems for red teaming, jailbreaks, or prompt injection.
OpenAI
We support AI safety testing projects, focusing on identifying and addressing risks before AI systems are deployed. We are a team of experts working on security, fairness, and domain-specific safety.