PhD Studentship, Monitoring and Increasing LLM Safety
Cambridge University, Department of Engineering · Added today
Applications are handled by the employer on an external website. AI Safety Careers does not process applications directly.
AI Safety & Alignment
Cambridge, UK
In this studentship, you'll pursue a PhD exploring large language model safety through mechanistic interpretability and behavioural research.
Investigate Chain-of-Thought faithfulness and detect deceptive behaviour via perturbation methods and mechanistic analysis.
Monitor LLM behaviour at inference time and develop risk reduction strategies.
Apply either perturbation techniques to test CoT meaning or train models for transparency using human predictor evaluation.
Collaborate with your supervisor to define research direction after completing initial 1.5-year projects.
This listing may be aggregated from a public source or submitted by a third party. If you represent this employer and would like to update or remove this listing, contact support@aisafetycareers.com.