Research Engineer / Scientist, Alignment Science, London

Core responsibilities:

• Build and run elegant and thorough machine learning experiments to understand and steer the behavior of powerful AI systems
• Contribute to exploratory experimental research on AI safety, with a focus on risks from powerful future systems
• Work on projects like testing the robustness of safety techniques, running multi-agent reinforcement learning experiments, and building evaluation tooling
• Contribute ideas, figures, and writing to research papers, blog posts, and talks

This role creates positive change by advancing AI safety research to ensure powerful AI systems remain safe, helpful, honest, and harmless, contributing to Anthropic's mission of building reliable, interpretable, and steerable AI systems that benefit society.

Required qualifications:

• Significant software, ML, or research engineering experience
• Some experience contributing to empirical AI research projects
• Some familiarity with technical AI safety research
• Preference for fast-moving collaborative projects over extensive solo efforts
• At least a Bachelor's degree in a related field or equivalent experience

Competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space for collaboration.

Anthropic is a frontier AI research and product company, with teams working on alignment, policy, and security. We post specific opportunities at Anthropic that we think may be high impact. We do not necessarily recommend working at other positions at Anthropic. You can read concerns about doing harm by working at a frontier AI company in our career review on the topic.