Research Engineer Intern

About the role

The Center for AI Safety (CAIS) is a leading research and field-building organization dedicated to reducing societal-scale risks from AI. We tackle tough AI issues through a combination of technical, societal, and policy solutions. As a research engineer intern, you will collaborate closely with our researchers on projects in areas like AI security, machine ethics, AI alignment, and benchmarking AI risks. You will work under a dedicated mentor but will be treated as a colleague, engaging in debates about your experiments and defending their impact.

Responsibilities

• Work on experiments and contribute to creating a publication with significant impact.
• Leverage our internal compute cluster to run experiments on large language models.
• Plan and run experiments, conduct code reviews, and collaborate in a small team.
• Read and understand ML papers, and integrate them into the broader literature.
• Set up, launch, and debug ML experiments.
• Familiarize yourself with relevant frameworks and libraries (e.g., PyTorch).
• Communicate clearly and promptly with teammates.
• Take ownership of your individual part in a project.

Requirements

• 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).
• Have a track record of empirical research in AI or ML, particularly in AI safety-relevant areas (e.g., adversarial robustness, calibration, benchmarking).
• Have made meaningful research contributions at a leading AI lab.
• Able to read and understand ML papers, and their place in the broader literature.
• Comfortable setting up, launching, and debugging ML experiments.
• Familiar with relevant frameworks and libraries (e.g., PyTorch).
• Communicate clearly and promptly with teammates.
• Take ownership of your individual part in a project.

Qualifications

• Strong background in machine learning or a related field.
• Experience with relevant frameworks and libraries (e.g., PyTorch).
• Track record of empirical research in AI or ML, especially in AI safety-relevant areas.
• Ability to set up, launch, and debug ML experiments.
• Good communication skills and ability to take ownership of tasks.

Skills

• Strong programming skills in Python or similar languages.
• Experience with large-scale data processing and model training.
• Understanding of machine learning theory and its practical applications.
• Ability to read and understand ML papers and their implications.
• Good teamwork and collaboration skills.

Benefits

The internship is unpaid but CAIS provides a stipend of $9,700 - $19,000 per year to assist with academic pursuits and living expenses. The stipend is subject to tax.

Pay

$9,700 - $19,000 per year.

Schedule

Full-time internship position.

Benefits

The internship is unpaid but CAIS provides a stipend of $9,700 - $19,000 per year to assist with academic pursuits and living expenses. The stipend is subject to tax.

Contact

If you require a reasonable accommodation during the application or interview process, please contact contact@safe.ai.

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.