GenAI CBRNE Cyber Expert, Intelligence

Adversarially test generative AI systems to identify vulnerabilities in safeguards against cyber-enabled CBRNE threats.
- Design and execute adversarial prompts, jailbreaks, and multi-turn attack scenarios to probe GenAI model vulnerabilities and safety bypasses.
- Develop realistic cyber-CBRNE attack scenarios involving critical infrastructure, industrial control systems, and high-consequence environments.
- Document failure modes, attack patterns, and severity classifications; provide actionable recommendations to AI safety teams.
- Requires deep cybersecurity expertise, CBRNE domain knowledge, and demonstrated red-teaming or offensive-security experience.
- Requires advanced degree in cybersecurity, computer science, or related field; GenAI red-teaming experience strongly preferred.

Alice is a trust, safety, and security AI company.