Senior GenAI Safety Researcher, Frontier Risk

Lead technical execution of frontier AI safety research, red-teaming, and risk mitigation across CBRNE and cybersecurity threat vectors.
- Execute red-teaming datasets, evaluation protocols, and technical risk reports across multimodal AI systems with rigorous QA checkpoints.
- Manage task allocation across subject-matter expert pools and maintain delivery velocity under compressed client deadlines.
- Present threat modeling, residual risk assessments, and architecture-level mitigations to client engineering and executive leadership.
- Requires 2–4 years in AI safety, red-teaming, CBRNE risk, or cyber threat intelligence with proven project leadership.
- Advanced degree in chemistry, biology, nuclear science, computer security, or AI preferred; offensive security experience a plus.

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