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.
Anthropic's Safeguards organization builds the policies, evaluations, and enforcement systems that define and hold the limits on how Claude can be used. In this role, you'll own our conventional weapons work.
Defining a crisp boundary between acceptable and harmful requests in this domain is difficult, because the underlying components are dual-use: the same capabilities that serve civilian engineering and research can also contribute to a weapons system. Building the threat models, evaluations, and detection systems that hold that boundary is the core of this role.
Conventional weapons are increasingly defined by software, and the risks re... Click Apply to read the full job description.