Researcher, Safety Oversight
Core
Develop AI monitor models and research strategies to detect, mitigate misuse, and maintain oversight of frontier AI systems to ensure safe deployment.
Role type
Senior AI safety researcher (AGI oversight)
Builds
AI monitor models, red-teaming pipelines, and research on human-AI collaboration and robustness
Domain
Artificial Intelligence / AI Safety / AGI
Deliverable
production ML models
Required skills
AI safety research, RLHF, human-AI collaboration, fairness & biases, model reasoning, Python
Preferred skills
Experience with large-scale AI systems, research engineering
Technologies
Python
Responsibilities
Develop and refine AI monitor models to detect and mitigate misuse; Set research directions for safer and more robust AI systems; Evaluate and design red-teaming pipelines; Conduct research on models' ability to reason about human values; Coordinate with cross-functional teams on safety standards