Research Engineer Intern (Fall 2026)
Quick answer
The Center for AI Safety is hiring a Fall 2026 Research Engineer Intern to collaborate on AI alignment, security, and benchmarking projects.
- Role
- Research Engineer Intern (Fall 2026)
- Organization
- The Center for AI Safety (CAIS)
- Level
- Entry
- Category
- Engineering & Technology
- Apply by
- 2026-06-15
The role
The Center for AI Safety is seeking a Research Engineer Intern for the Fall 2026 term to work on critical projects in AI security, ethics, alignment, and risk benchmarking. Interns will operate as colleagues, collaborating directly with researchers to plan experiments, conduct code reviews, and drive impactful publications using internal compute resources. This role provides a dedicated mentor and requires active participation in project debates and experimental design.
What you'll do
- Collaborate with researchers on AI security and alignment projects.
- Plan and execute experiments at scale using internal compute clusters.
- Conduct code reviews and contribute to research publications.
- Engage in technical debates regarding project impact and methodology.
What it takes
- Current university enrollment in machine learning or a related field.
- Co-authorship of at least one paper at a top ML conference (e.g., NeurIPS, ICML).
- Demonstrated track record of empirical research in AI safety-relevant areas.
- Proficiency in ML frameworks and libraries, specifically PyTorch.
- Ability to interpret ML literature and communicate results clearly.
What you'll bring
How we treat you
Dedicated mentorship and access to internal compute clusters for large-scale experiments.
Frequently asked questions
What is the application deadline for this internship?
Applications for the Fall 2026 internship are due by June 15, 2026.
Who is eligible to apply for this position?
Applicants must be currently enrolled in a university degree program, with a preference for candidates who have co-authored papers at top ML conferences.
What will I be doing as a Research Engineer Intern?
You will work closely with researchers to design, launch, and debug machine learning experiments while contributing to publications in areas like AI safety and alignment.
Is this position remote or in-person?
The job description does not explicitly specify whether the position is remote, hybrid, or in-office.
How to apply
Apply directly on The Center for AI Safety (CAIS)'s site. We link straight through — no resume parsing, no profile to fill out.
This listing is aggregated from a third-party source and its summary may be auto-generated, so details can be inaccurate or out of date. ForGood is not the employer and is not liable for the content — please verify everything on The Center for AI Safety (CAIS)'s official posting before applying.