About the Role
Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems. The Frontier Red Team at Anthropic plays a crucial role in pushing the boundaries of AI safety. This team is dedicated to proactively identifying and mitigating risks associated with advanced AI systems, especially those demonstrating increasing levels of autonomy. As a Research Engineer on the Frontier Red Team focusing on Autonomy, you will be at the forefront of understanding and addressing the unique safety challenges posed by highly autonomous AI. You will design and execute experiments to probe the limits of AI systems, develop novel red-teaming techniques, and contribute to the development of robust safety mechanisms. This role requires a strong research background, a deep understanding of AI systems, and a passion for ensuring AI is developed responsibly and beneficially.
Responsibilities
- Design and execute experiments to probe the limits of AI systems
- Develop novel red-teaming techniques
- Contribute to the development of robust safety mechanisms
Requirements
- Strong research background
- Deep understanding of AI systems
- Passion for ensuring AI is developed responsibly and beneficially
- At least a Bachelor's degree in a related field or equivalent experience.
Benefits
Anthropic is a public benefit corporation headquartered in San Francisco. We offer competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space in which to collaborate with colleagues. Location-based hybrid policy: Currently, we expect all staff to be in one of our offices at least 25% of the time. Visa sponsorship: We do sponsor visas!