Head of Cyber Safety, Red Team

Lead Gray Swan's cyber safety capability, evaluating frontier AI systems for offensive cyber risks and building scalable defenses.
- Design adversarial evaluations of LLMs for offensive cyber capabilities including vulnerability discovery, exploit development, and autonomous operations.
- Partner with ML engineers to translate cybersecurity expertise into benchmarks, guardrails, detection systems, and evaluation infrastructure.
- Build and mentor a team of cybersecurity experts while establishing evaluation processes, quality standards, and technical infrastructure.
- Requires deep offensive cybersecurity expertise through industry or research experience plus hands-on AI red-teaming or LLM security evaluation.
- Requires comfort operating at the intersection of cybersecurity research, AI safety, and machine learning in ambiguous environments.

Gray Swan is an AI security company that develops tools that automatically assess the risks of AI models.