I am hiring a postdoctoral researcher to work on security and trustworthy generative AI, including training-data attribution, model memorization, provenance, and auditing of generative models.
The ideal candidate holds (or is completing) a Ph.D. in computer science or a related field, with a strong publication record in machine learning, security, or a related area. The position is fully funded.
To apply, email me your CV.
I am recruiting 1-2 fully funded PhD students to join my group at Dartmouth College starting in Fall 2027.
If you are interested in research at the intersection of trustworthy AI and security, you are encouraged to:
If you are a current Dartmouth undergraduate or master's student interested in research, feel free to reach out.
I am always happy to talk with motivated students interested in working on projects in ML security and AI misuse. Please email me with your CV and a few sentences about what you are excited to explore.