Researcher, Robustness & Safety Training
San Francisco • FullTime
Posted 3y ago
Remote Work Policy
On-site
Employment Type
FullTime
Categories
AI Research Engineer
About the job
OpenAI is seeking a senior researcher passionate about AI safety to set research directions and conduct projects aimed at making AI systems safer, more aligned, and robust against adversarial or malicious use cases. This role is critical in shaping the future of safe AI systems at OpenAI and significantly impacting the mission to build and deploy safe AGI. The Safety Systems team focuses on ensuring AI models can be safely deployed to benefit society, advancing capabilities for robust and safe AI behavior, and addressing challenges as AI becomes more powerful and widely used.
Responsibilities
- Conduct state-of-the-art research on AI safety topics like RLHF, adversarial training, and robustness.
- Implement new methods in core model training and launch safety improvements in products.
- Set research directions and strategies for AI system safety, alignment, and robustness.
- Coordinate with cross-functional teams (T&S, legal, policy, research) to meet high safety standards.
- Evaluate and understand model/system safety, identifying risks and proposing mitigation strategies.
Requirements
- 4+ years of experience in AI safety, particularly in RLHF, adversarial training, robustness, fairness & biases.
- Ph.D. or other degree in computer science, machine learning, or a related field.
- Experience in safety work for AI model deployment.
- In-depth understanding of deep learning research and/or strong engineering skills.
- Team player with experience in collaborative work environments.
- Excited about OpenAI's mission of building safe, universally beneficial AGI and aligned with OpenAI's charter.
- Passion for AI safety and making cutting-edge AI models safer for real-world use.