Researcher, Safety Oversight

Highlights

• Develop AI monitor models to detect and mitigate misuse and misalignment.
• Advance scalable oversight and human-AI collaboration for frontier models.
• Design red-teaming pipelines to test end-to-end robustness of safety systems.

What they offer

• Equity

Ideal candidate

Safety-driven researcher with 4+ years in AI safety who thrives on large-scale systems and cares deeply about building safe, beneficial AGI aligned with human values.

Requirements

• 4+ years of experience in AI safety, especially RLHF, human-AI collaboration, fairness & biases
• Ph.D. or other degree in computer science, machine learning, or a related field
• 4+ years of research engineering experience and proficiency in Python or similar languages
• Thrive in environments involving large-scale AI systems
• Enthusiasm for AI safety and dedication to enhancing safety of cutting-edge AI models