Researcher, Frontier Risk Mitigations
Core
Developing novel safety mitigations and techniques (interpretability, control, alignment) to derisk frontier AI models and ensure safe deployment.
Role type
Senior research engineer specializing in AI safety and frontier risk mitigation
Builds
End-to-end safety stack, evaluation pipelines, and red-teaming frameworks for frontier AI systems
Domain
Artificial Intelligence Safety, Frontier Risk Mitigation, AGI Alignment
Deliverable
production ML models | research
Required skills
AI safety research, RLHF, human-AI collaboration, interpretability, control theory, robustness analysis, Python programming, research engineering
Preferred skills
Experience with cybersecurity, biology, or misalignment domains
Technologies
Python
Responsibilities
Identify emerging AI safety risks and develop methodologies to mitigate them; build and refine evaluation systems to assess risk extent; set research directions for safer and more aligned AI systems; design effective red-teaming pipelines to test safety system robustness; contribute to industry best practices for AI safety
Seniority
Senior, hands-on IC with research and engineering responsibilities