Research Engineer Intern (Fall 2026)

About this role

CAIS seeks a Research Engineer Intern to contribute to cutting-edge AI safety research in San Francisco, working on projects spanning security, ethics, alignment, and risk benchmarking. You'll collaborate closely with experienced researchers, design and execute experiments on large language models, and help produce impactful publications while receiving dedicated mentorship.

What you'll do

• Design and run experiments on large language models using internal compute infrastructure
• Collaborate with researchers on AI safety projects including security, ethics, and alignment
• Plan and execute research initiatives with opportunity to propose your own directions
• Conduct code reviews and contribute to technical implementation
• Participate in team efforts to develop publications with significant research impact
• Engage in technical discussions and defend experimental approaches

What they're looking for

• Machine learning and AI system development
• Experiment design and execution
• Python or similar programming languages
• Code review and software engineering practices
• Large language model experience
• Research methodology
• Technical communication and presentation
• Problem-solving in complex AI systems

Benefits

• Dedicated mentor throughout internship
• Autonomy to propose and defend your own research projects
• Access to internal compute cluster for large-scale experiments
• Opportunity to contribute to published research
• Collaborative work with leading AI safety researchers
• Full-time internship opportunity