Responsibilities

As a Research Engineer, you will build and run elegant and thorough machine learning experiments to understand and steer the behavior of powerful AI systems, focusing on AI safety and risks from future systems. You will contribute to exploratory experimental research, often in collaboration with other teams, and develop techniques for scalable oversight, AI control, and alignment stress-testing. Specifically, you will conduct projects such as testing the robustness of safety techniques, running multi-agent reinforcement learning experiments, building tooling to evaluate jailbreaks, writing scripts and prompts for evaluation questions, and contributing to research papers, blog posts, and talks. You will also run experiments that feed into key AI safety efforts, like the design and implementation of Anthropic's Responsible Scaling Policy.