March 14
🏢 In-office - San Francisco
• Research and field-building nonprofit focused on reducing catastrophic risks from artificial intelligence • Research engineer intern role working on projects related to Trojans, Adversarial Robustness, Power Aversion, Machine Ethics, and Out-of-Distribution Detection • Treat interns as colleagues with the opportunity to debate for own experiments, plan and run experiments, and create publications • Collaboration with Center for AI Safety in steering the future of AI
• Able to read ML papers and understand key results • Comfortable setting up, launching, and debugging ML experiments • Familiar with relevant frameworks and libraries like pytorch • Clear and prompt communication with teammates • Ownership of individual project parts • Co-authored a ML paper in a top conference
• Opportunity to work closely with researchers on impactful projects • Assigned dedicated mentor • Opportunity to plan and run experiments, conduct code reviews, and work in a small team • Leverage internal compute cluster for experiments • Start of potential long-term collaboration
Apply Now