Emmanuel Ameisen works on the Interpretability Research team at Anthropic, which focuses on understanding how large language models think and process information. Most recently, he led efforts to trace the internal reasoning steps of AI models as they respond to prompts, creating a kind of "AI microscope" to peer inside them. Previously, he worked on model fine tuning, training Claude to be better at programming and tool use. Before joining Anthropic, he served as a Staff Machine Learning Engineer at Stripe and led Insight Data Science's AI program where he directed over a hundred machine learning projects. Emmanuel is also the author of the O'Reilly book "Building Machine Learning Powered Applications: Going from Idea to Product," which provides practical guidance on deploying ML systems in production.