About The Center for AI Safety (CAIS) The Center for AI Safety (CAIS) is a leading research and advocacy organization focused on mitigating societal-scale risks from AI. Some of our past achievements include: releasing the most widely used measure of AI capabilities used by all major AI companies, running a large compute cluster to facilitate AI safety research which has been cited over 16,000 times , and publishing a global statement on AI Risk signed by Geoffrey Hinton, Yoshua Bengio and top AI CEOs. The Role As a research engineer intern here, you will work very closely with our researchers on projects in areas such as AI security, machine ethics, AI alignment, and benchmarking AI risks. 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. There is no application deadline. We review applications on a rolling basis and take interns for the fall, winter, spring, and summer terms. These are full-time internships, and we are happy to work out start and end dates with you. Applicants must be enrolled in university to be considered. We are generally flexible about when we review applications. If you are not sure which term fits, put in an application anyway and we will get back to you if we think it is a good fit. What We're Looking For - Are a current student in machine learning or a related field. Exceptional candidates with a strong publication record may be considered regardless of degree level. - Have co-authored at least one paper published at a top ML conference venue (e.g., NeurIPS, ICML, ICLR, ACL, CVPR). Workshop papers are considered, though peer-reviewed conference publications are strongly preferred. Publications in journals such as IEEE or Springer Nature are typically given less weight. - Have a track record of empirical research in AI or ML, particularly in AI safety-relevant areas (e.g. adversarial robustness, calibration, benchmarking). We weight empirical research heavily; candidates with primarily theoretical backgrounds are generally not a strong fit. - Alternatively, have made meaningful research contributions at a leading AI lab. - Are able to read an ML paper, understand the key result, and understand how it fits into the broader literature. - Are comfortable setting up, launching, and debugging ML experiments. - Are familiar with relevant frameworks and libraries (e.g., PyTorch). - Communicate clearly and promptly with teammates. - Take ownership of your individual part in a project. Stipend $9,700 - $19,000, based on academic experience. This internship is unpaid; however, CAIS provides the above stipend to assist with academic pursuits and living expenses. The stipend is subject to tax. Referral Program Know someone who could be a great fit for this role? Submit their details through our Referral Form . If we end up hiring your referral, you’ll receive a $1,500 bonus once they’ve been with CAIS for 90 days. Equal Opportunity Employer The Center for AI Safety is an Equal Opportunity Employer. We consider all qualified applicants without regard to race, color, religion, sex, sexual orientation, gender identity or expression, national origin, ancestry, age, disability, medical condition, marital status, military or veteran status, or any other protected status in accordance with applicable federal, state, and local laws. In alignment with the San Francisco Fair Chance Ordinance, we will consider qualified applicants with arrest and conviction records for employment. If you require a reasonable accommodation during the application or interview process, please contact contact@safe.ai. We value diversity and encourage individuals from all backgrounds to apply.