Research Engineer Intern (Fall 2025)

In this role, you'll work closely with researchers on AI safety projects in fields like Trojans, Adversarial Robustness, and Machine Ethics. Collaborate with a dedicated mentor while being treated as a colleague with input on experiments and projects. Plan and run experiments on large language models using CAIS's internal compute cluster. Conduct code reviews and work in small teams to create impactful publications. Leverage your ML expertise to understand papers, debug experiments, and contribute to reducing societal-scale risks from AI.

The Center for AI Safety is a nonprofit conducting technical research and field building for high-consequence risks from AI. This includes providing compute for machine learning safety researchers, and running fellowships and courses.