Technical Lead, Safety Research
Core
Developing strategy and conducting research to ensure AI systems are safe, aligned, and robust for real-world deployment.
Role type
Senior IC technical lead in AI safety research
Builds
Safer, more aligned, and robust AI models and systems for OpenAI products
Domain
Artificial Intelligence / Machine Learning / AI Safety
Deliverable
production ML models
Required skills
AI safety research, alignment research, RLHF, adversarial training, robustness evaluation, deep learning research, strategy setting, cross-functional collaboration
Preferred skills
Experience in safety work for AI model deployment, engineering skills
Technologies
RLHF, adversarial training
Responsibilities
Set research directions and strategies to improve AI safety; Conduct state-of-the-art research on AI safety topics; Evaluate and understand model safety to identify risks and propose mitigations; Implement new methods in core model training and launch safety improvements
Seniority
Senior, hands-on IC with strategic leadership