Jobs

Anthropic is seeking a Research Scientist for their Interpretability team to reverse-engineer how trained models work, aiming for a mechanistic understanding to ensure advanced AI systems are safe. This role involves developing methods for understanding LLMs, designing and running experiments, and building infrastructure for interpretability research. The ideal candidate has a strong scientific research background, enjoys collaborative team science, and views research and engineering as intertwined, with proficiency in Python required. Join Anthropic to contribute to creating reliable, interpretable, and steerable AI systems.