Research Engineer Intern

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 its 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.

About the role

As a research engineer intern, you will work very closely with researchers on projects in areas such as AI security, machine ethics, AI alignment, and benchmarking AI risks. You will be assigned a dedicated mentor throughout the internship and treated as a colleague, with opportunities to propose and defend your own experiments or projects. Responsibilities include planning and running experiments, conducting code reviews, and collaborating in a small team to produce publications with outsized impact. You will leverage the internal compute cluster to run experiments at scale on large language models.

This application is for the full-time fall internship position. Applicants must be enrolled in university to be considered.

What we're looking for

• Current student in machine learning or a related field; exceptional candidates with a strong publication record may be considered regardless of degree level.
• 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.
• Track record of empirical research in AI or ML, particularly in AI safety-relevant areas (e.g., adversarial robustness, calibration, benchmarking); empirical research is heavily weighted and candidates with primarily theoretical backgrounds are generally not a strong fit.
• Alternatively, meaningful research contributions at a leading AI lab.
• Ability to read an ML paper, understand the key result, and place it within the broader literature.
• Comfort with setting up, launching, and debugging ML experiments.
• Familiarity with relevant frameworks and libraries (e.g., PyTorch).
• Clear and prompt communication with teammates.
• Ownership of your individual part in a project.

Stipend

$3,233 – $6,333. This internship is unpaid; CAIS provides the above stipend to assist with academic pursuits and living expenses. The stipend is subject to tax.