Center for AI Safety

Research Engineer

• Work very closely with researchers on projects in Trojans, Adversarial Robustness, Power Aversion, Machine Ethics, and Out-of-Distribution Detection.
• Plan and run experiments, set up, launch, and debug ML experiments.
• Conduct code reviews and collaborate in a small team to create publication-quality work.
• Leverage internal compute cluster to run experiments at scale on large language models.
• Debate and defend your experiments or projects; take ownership of individual contributions.
• Be assigned and work with a dedicated mentor throughout the internship.

Research Engineer Intern