Cornell University | Postdoctoral Fellowship in AI Mechanistic Interpretability
Applied mathematician Dr. Chris Earls is looking to hire a postdoc at Cornell Univerwity. The area — interpretability of emergent behaviors exhibited by AI systems — is fascinating and important.
Cornell University | Postdoctoral Fellowship in AI Mechanistic Interpretability
General Information
- Lab: Earls Group (College of Engineering)
- Research Focus: Understanding and rigorously describing the mechanistic basis for emergent behaviors exhibited by state-of-the-art AI system.
- Key Responsabilities: Conduct independent research, pursue novel research directions, publish, present at meetings, and function as an effective team member within the Earls Group.
- Requirements: PhD in applied mathematics, mathematics, physics, or a related field; string publication record; and a very strong interest in AI mechanistic interpretability research.
- Duration: 24 months with a start date no later than July 1, 2026.
- To Apply: Before May 1, 2026, email a cover letter (detailing research interest and fit), an academic CV, and the contact information for three references to earls@cornell.edu
Application and more details: https://earls.cee.cornell.edu/
This post is licensed under CC BY 4.0 by the author.