Description
Center for AI Safety (CAIS) is hiring a research engineer intern for a full-time fall internship focused on AI safety research. The intern will work closely with researchers on projects in AI security, machine ethics, AI alignment, and benchmarking AI risks, planning and running experiments, conducting code reviews, and contributing to a publication using an internal compute cluster to run large-scale experiments on large language models. Applicants must be enrolled in university and have strong machine learning or research experience, ideally including top conference publications and familiarity with PyTorch and ML experimentation.
