AI Safety Research Engineer Intern

Center for Ai Safety; San Francisco (CA); On-site; USD 9,700 - 19,000; Full time

Benefits offered by this job

Stipend

Job summary

The Center for AI Safety in San Francisco invites a Research Engineer Intern to work closely with our researchers on AI safety, ML alignment, and benchmarking. You will plan and run experiments, review code, and contribute to publications, using our compute cluster to scale experiments on large language models.

You will have a dedicated mentor and be treated as a colleague within a small team. Applicants must be enrolled in university for a full-time fall internship, with stipends ranging from

Qualifications

• Currently a student in machine learning or a related field.
• At least one paper published in a top ML conference (e.g., NeurIPS/ICML/ICLR/ACL/CVPR).
• Experience with empirical AI/ML research, especially safety-related areas.
• Able to read ML papers and relate results to literature.
• Comfortable setting up, launching, and debugging ML experiments.

Responsibilities

• Plan and run experiments with researchers on AI safety topics.
• Conduct code reviews and collaborate with a small team.
• Contribute to publications with outsized impact.
• Leverage internal compute cluster to scale experiments on LLMs.

Skills

Machine Learning

Empirical Research

PyTorch

Communication

Ownership

Education

Enrollment in university

Tools

PyTorch

Job description

The Center for AI Safety in San Francisco invites a Research Engineer Intern to work closely with our researchers on AI safety, ML alignment, and benchmarking. You will plan and run experiments, review code, and contribute to publications, using our compute cluster to scale experiments on large language models.

You will have a dedicated mentor and be treated as a colleague within a small team. Applicants must be enrolled in university for a full-time fall internship, with stipends ranging from