Researcher, Safety Oversight
San Francisco • FullTime
Posted 1y ago
About the job
OpenAI is seeking a senior researcher passionate about AI safety to join the Safety Oversight Research team. This role will be instrumental in setting research directions to ensure safe AGI and will focus on identifying and mitigating misuse and misalignment in AI systems. You will play a critical part in defining the future of safe AI systems at OpenAI, significantly impacting our mission to build and deploy safe AGI. The Safety Systems team is dedicated to ensuring our advanced models can be safely deployed for societal benefit, driving our commitment to AI safety and fostering trust and transparency.
Responsibilities
- Develop and refine AI monitor models to detect and mitigate misuse and misalignment.
- Set research directions and strategies to enhance AI system safety, alignment, and robustness.
- Evaluate and design red-teaming pipelines to assess safety system robustness and identify improvement areas.
- Conduct research to improve models' reasoning about human values and apply findings to practical safety challenges.
- Collaborate with cross-functional teams to ensure products meet high safety standards.
Requirements
- 4+ years of experience in AI safety research.
- Experience in areas like RLHF, human-AI collaboration, fairness, and biases.
- Ph.D. or equivalent degree in computer science, machine learning, or a related field.
- Experience in environments with large-scale AI systems.
- 4+ years of research engineering experience.
- Proficiency in Python or similar languages.