Researcher, Robustness & Safety Training
Core
Conduct state-of-the-art research on AI safety topics such as RLHF, adversarial training, robustness, and fairness to enable safe AGI deployment.
Role type
Senior AI safety researcher
Builds
New methods in core model training and safety improvements in products
Domain
Artificial Intelligence / Machine Learning Safety
Deliverable
production ML models
Required skills
RLHF, adversarial training, robustness, fairness & biases, deep learning research, AI model deployment safety
Preferred skills
engineering skills
Technologies
RLHF, adversarial training
Responsibilities
Conduct state-of-the-art research on AI safety topics, Implement new methods in core model training, Set research directions and strategies for safety, Coordinate with cross-functional teams, Evaluate and understand model safety
Seniority
Senior, hands-on IC
Sourced via ashby · Listed on CareerPlan, which tracks 70,000+ jobs from 20+ sources.