CU
PhD studentship researching LLM safety via mechanistic interpretability, behavioral research, deceptive behavior detection, and inference-time monitoring to reduce model risk.
Salary not disclosed
A weekly digest of AI safety, governance, policy and responsible AI roles.
By subscribing, you agree to receive the AI Safety Careers newsletter. We use MailerLite to send emails and may track opens and clicks to improve the newsletter. You can unsubscribe at any time. See our Privacy Policy.
1 active role found for Cambridge University, Department of Engineering
PhD studentship researching LLM safety via mechanistic interpretability, behavioral research, deceptive behavior detection, and inference-time monitoring to reduce model risk.