About the job
About Anthropic
At Anthropic, we are dedicated to developing AI systems that are not only reliable and interpretable but also safe and beneficial for both our users and society at large. Our rapidly expanding team comprises passionate researchers, engineers, policy experts, and business leaders who collaborate to create cutting-edge AI technologies.
Note: Although we are not actively hiring for this team at this moment, we are collecting expressions of interest. If we find a mutual fit when we resume hiring, we may reach out to you.
About the Role
In the capacity of a Research Engineer on our Model Evaluations team, you will spearhead the design and implementation of Anthropic's evaluation platform. This platform is crucial for understanding, measuring, and enhancing the capabilities and safety of our models. You will engage at the crossroads of research and engineering, producing insightful evaluations that inform our training decisions and shape our model development trajectory.
Your contributions will play a pivotal role in fulfilling Anthropic's mission of building safe and beneficial AI systems. Collaborating closely with training teams, alignment researchers, and safety experts, you will help ensure our models adhere to the highest standards prior to deployment. This position entails both strategic leadership and hands-on implementation of our evaluation systems.

