Researcher Safety Oversight (AI)

TL;DR

Researcher Safety Oversight (AI): Conduct research to develop and refine AI safety and oversight systems ensuring safe deployment of AGI with an accent on AI misuse detection, model robustness, and human values alignment. Focus on designing red-teaming pipelines, scalable oversight methods, and collaborating cross-functionally to maintain high safety standards.

Location: Onsite in San Francisco, United States

Salary: $310,000–$460,000 + Equity

Company

OpenAI is an AI research and deployment company dedicated to building safe and beneficial general-purpose artificial intelligence for all humanity.

What you will do

• Develop and refine AI monitor models to detect and mitigate misuse and misalignment.
• Set research directions and strategies to improve AI system safety, alignment, and robustness.
• Design and evaluate red-teaming pipelines for end-to-end safety system robustness.
• Conduct research on models' reasoning about human values and apply to safety challenges.
• Collaborate with cross-functional teams including legal, policy, and research to ensure safety standards.

Requirements

• Must be located onsite in San Francisco, United States.
• 4+ years of AI safety research experience, especially in RLHF, human-AI collaboration, fairness, and bias.
• Ph.D. or equivalent degree in computer science, machine learning, or related field.
• 4+ years of research engineering experience with proficiency in Python or similar languages.
• Strong dedication to AI safety and alignment with OpenAI's mission and charter.

Culture & Benefits

• Equal opportunity employer with commitment to diversity and inclusion.
• Competitive compensation including salary and equity.
• Work in a mission-driven environment focused on safe AGI deployment.
• Access to cutting-edge AI research and collaboration with top experts.