Introduction The Center for AI Safety (CAIS) is a leading research and field-building organization on a mission to reduce societal-scale risks from AI. Alongside our sister organization, the CAIS Action Fund, we tackle the toughest AI issues with a mix of technical, societal and policy solutions. Our work includes publishing a global statement on AI Risk signed by Geoffrey Hinton, Yoshua Bengio and CEOs from the major AI labs, leading the charge on a major AI safety bill, and running a large compute cluster for global academic researchers working on AI safety research.

As a research engineer intern here, you will work very closely with our researchers on projects in fields such as Trojans, Adversarial Robustness, Power Aversion, Machine Ethics, and Out-of-Distribution Detection. We will assign you a dedicated mentor throughout your internship, but we will ultimately be treating you as a colleague. By this we mean, you will have the opportunity to debate for your own experiments or projects, and defend their impact. You will plan and run experiments, conduct code reviews, and work in a small team to create a publication with outsized impact. You will leverage our internal compute cluster to run experiments at scale on large language models. We hope you will view this opportunity as the start of a long-term collaboration with CAIS.

Timing This application is for the fall internship position. Applications are due by July 19, 2025.