Research Fellowship, Cryptographic Verification Mechanisms for Training AI Models
General-Purpose AI Policy Lab · Added 3 days ago
Applications are handled by the employer or external application platform. AI Safety Careers does not process applications directly.
Paris, France
€1,000 per month
In this role, you'll advance cryptographic verification mechanisms for AI training.
Implement zero-knowledge circuits in Rust to encode GPU operations and training computations.
Develop an NCCL wrapper to capture and log distributed training communications between nodes.
Address open research problems in threat models, provable properties, and system architecture.
Produce research supporting international coordination on AI safety and verification standards.
The General Purpose AI Policy Lab is a French organization specializing in security and international coordination issues raised by frontier general-purpose AI models.
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.