[Expression of Interest] Research Manager, Interpretability

Who you are

You are excited about interpretability research and have a strong interest in AI safety. You may have experience in research roles, particularly in understanding complex systems and their mechanisms. You are open to contributing as an individual contributor in a growing team focused on AI interpretability. You understand the importance of creating reliable and interpretable AI systems that benefit users and society.

Desirable

Experience in AI research or related fields is a plus. Familiarity with mechanistic interpretability and neural networks will help you thrive in this role. You are a collaborative team player who enjoys working with researchers, engineers, and policy experts to advance the mission of AI safety.

What you'll do

As a Research Manager, you will engage in interpretability research, focusing on reverse engineering how trained models work. You will collaborate with a diverse team to build a solid scientific foundation for understanding neural networks. Your work will contribute to making advanced AI systems safe and beneficial. You will be involved in discussions about the implications of AI interpretability and how it can enhance user trust in AI technologies.

What we offer

Anthropic offers a competitive compensation package and benefits, including generous vacation and parental leave. You will have flexible working hours and the opportunity to work in a collaborative office space in San Francisco. We are committed to creating a supportive environment where you can grow and contribute to meaningful AI research.