PeopleofSuperintelligence

Researcher

Emmanuel Ameisen

Emmanuel Ameisen is an interpretability researcher at Anthropic whose work studies how language models operate internally. He built machine-learning systems for Local Motion and Zipcar, led Insight Data Science's AI program, and holds graduate degrees in artificial intelligence, computer engineering, and management. He published a guide to building machine-learning applications in 2020 and worked on Claude fine-tuning and interpretability at Anthropic by 2024. His later work examines hidden model objectives, traces circuits inside language models, and studies how models detect changes to their internal representations.

Timeline

  1. 2018–2020

    Insight's AI program

    In October 2018, he leads Insight Data Science's AI program and develops an image-search system using convolutional neural networks and word embeddings. Before Insight, he builds and deploys predictive-analytics and machine-learning systems for Local Motion and Zipcar; by 2020, he holds graduate degrees in artificial intelligence, computer engineering, and management from three French schools.

  2. January 2020

    A book on applied ML

    He publishes Building Machine Learning Powered Applications: Going from Idea to Product in January 2020. The book guides readers through designing, building, and deploying a machine-learning application from its initial idea.

  3. August 2024

    Research Engineer at Anthropic

    In August 2024, he is a Research Engineer at Anthropic, where he fine-tunes Claude and helps with interpretability research.

  4. March 2025

    Auditing hidden model objectives

    He coauthors Auditing language models for hidden objectives in March 2025. The study trains a model with a hidden objective, runs a blind auditing game with four research teams, and examines eight auditing techniques.

  5. May 2025

    Open-sourcing circuit-tracing tools

    In May 2025, Anthropic releases a circuit-finding library developed by fellows Michael Hanna and Mateusz Piotrowski with mentorship from Emmanuel Ameisen and Jack Lindsey. The tools let researchers trace model circuits, visualize graphs, and test hypotheses by changing feature values.

  6. 2026

    Mechanisms of introspective awareness

    In 2026, he coauthors Mechanisms of Introspective Awareness, which studies how language models detect injected steering vectors and identify the injected concept. The paper finds that distributed internal computations support this detection.

  7. As of October 2026

    Interpretability research at Anthropic

    He is an interpretability researcher at Anthropic, where he focuses on understanding how large language models work internally.

Videos

YouTube videos in which Emmanuel Ameisen speaks or appears, newest first. A model chose them from YouTube search results. List updated 19 October 2026.

  1. Inside the “Neurons” of LLMs: Circuit Tracing Their Hidden Biology [Emmanuel Ameisen] - 727The TWIML AI Podcast with Sam Charrington · 15 April 2025 · 1 h 34 min
  2. Turning Ideas into ML Powered Products with Emmanuel Ameisen - #349The TWIML AI Podcast with Sam Charrington · 17 February 2020 · 43 min

Video data from YouTube API Services. By watching you agree to the YouTube Terms of Service. How we use YouTube data.

  1. Google had the most people shaping AI every year from 2014 to 2025Our estimates of which organizations employed the most people shaping AI from 1961 to 2025, with a year-by-year chart.
  2. The United States employs an estimated 53% of people in our data with a known employment countryOur estimates of where AI careers are concentrated now and how countries’ shares of dated positions changed over time.
  3. 46% of living people in our data with known birth and employment countries work outside their birth countryOur estimate of cross-border careers in AI, from country of birth and the country of each current organization.
  4. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionOur estimates of where the people shaping AI studied and where their careers led, from education records in cited biographies.

Sources and credits

Photo: We have no published photo of Emmanuel Ameisen yet. Send us a free-licensed photo.

  1. Emmanuel Ameisen, Head of AI at Insight, on Building a Semantic Search System for Images infoq.com. Checked 19 October 2026.
  2. Emmanuel Ameisen — AI Council aicouncil.com. Checked 19 October 2026.
  3. Building Machine Learning Powered Applications: Going from Idea to Product - Emmanuel Ameisen - Google Books books.google.com. Checked 19 October 2026.
  4. Integrating LLMs Into Products - Video | Agentic AI Foundation home.mlops.community. Checked 19 October 2026.
  5. Auditing language models for hidden objectives arxiv.org. Checked 19 October 2026.
  6. Open-sourcing circuit-tracing tools anthropic.com. Checked 19 October 2026.
  7. Mechanisms of Introspective Awareness proceedings.mlr.press. Checked 19 October 2026.
  8. The AI Conference 2026 Speakers: Full Lineup | Mezzo talkmezzo.com. Checked 19 October 2026.