Researcher, Frontier Risk Mitigations

Overview

Researcher role focused on frontier AI safety mitigations for OpenAI’s deployed models.

What you'll do

• Identify emerging AI safety risks and methodologies to explore and mitigate their impact.
• Build and continuously refine evaluations to assess the extent of frontier risks.
• Set research directions and strategies to make AI systems safer, more aligned, and more robust.
• Contribute to “best practices” guidelines for AI safety for OpenAI and the industry.
• Evaluate and design red-teaming pipelines to test end-to-end robustness of safety systems.

What you'll need

• 2+ years of experience in AI safety, especially in RLHF, human-AI collaboration, interpretability, or control.
• Python (or similar languages) proficiency.
• 4+ years of research engineering experience.
• A Ph.D. or other degree in computer science, machine learning, or a related field.
• Technical depth and ability to collaborate closely across functions.
• Experience in large-scale AI systems environments.