Research Engineer, Interpretability

Anthropic is seeking a Research Engineer for their Interpretability team in London. The role focuses on reverse engineering how trained models work, with the goal of making advanced AI systems safe through mechanistic understanding. Key responsibilities include implementing research experiments, optimizing workflows, building tools for rapid experimentation, and developing infrastructure to support model safety improvements. The ideal candidate should have 5-10+ years of software engineering experience, proficiency in programming languages (especially Python), and a strong ability to prioritize impactful work. Experience with machine learning, language modeling, and GPU optimization is beneficial. The role offers competitive compensation, including a salary range of £230,000 — £515,000 GBP, equity, and comprehensive benefits. Anthropic values diversity and encourages applications from underrepresented groups. The company operates on a hybrid work model, requiring at least 25% in-office presence, and offers visa sponsorship for eligible candidates.