Research Scientist

Conduct rigorous research on frontier AI safety and security through pilot audits and evaluations with AI companies.
- Design and run evaluations of AI systems' capabilities, risks, robustness, and alignment-relevant behavior; develop audit methods and protocols.
- Build reproducible experimental pipelines, produce audit reports, and translate technical findings into actionable recommendations for developers and policymakers.
- Collaborate with researchers, engineers, policy experts, and standards bodies to shape frontier AI auditing as a field.
- Requires 3+ years independent AI/ML research beyond PhD, preferably in AI safety, evaluations, robustness, or security.
- Experience with large language models in safety-relevant contexts and ability to design rigorous empirical studies essential.

The AI Verification and Evaluation Research Institute is a nonprofit that aims to bring about a world in which the most powerful AI systems and the companies that build them are rigorously audited for safety and security by third parties.