Senior GenAI Safety Researcher: Frontier Risk

Role overview Lead research delivery on frontier AI safety risks, with particular attention to chemical, biological, radiological and nuclear (CBRNE) and cybersecurity threats. You’ll coordinate researchers and client partners, oversee evaluations across text, image and audio systems, and turn complex threat findings into practical mitigations for engineering and safety leaders.

Responsibilities - Lead development of red-team datasets, evaluation methods and technical risk reports. - Establish quality checks for base models, guardrails and agentic workflows across modalities. - Coordinate specialist capacity and task assignments to meet demanding client timelines. - Review analytical methods and outputs for rigor, reproducibility and dual-use safeguards. - Present threat models, residual risks and architecture-level mitigations to client engineering teams. - Track emerging AI capabilities and update evaluation frameworks for CBRNE and cyber risks.

Benefits and work setup The position is remote within the United States.