ÂÜÀòÂÒÂ×

Walter Laurito is a Doctoral Researcher at FZI Forschungszentrum Informatik, focusing on the interpretability of large language models (LLMs) and AI safety since May 2020. Laurito also serves as a Research Engineer and Team Lead at Cadenza Labs, where work involves interpretability research in machine learning models. In addition, Laurito is involved with the AI Safety Engineering Taskforce as a Research Engineer, contributing to the AI Safety Institute's inspect_ai framework. Previous experience includes mentorship at the Berkeley AI Safety Student Initiative, a position as an AI Safety Scholar with the Stanford Existential Risks Initiative, and participation in AI and ML safety projects at Prague Fall Season. Earlier in the career, Laurito worked as a Web and Mobile Developer in freelance roles and held software development positions at companies like Scorpius Forge GmbH and ml webservices. Academic credentials include a Master's degree in Computer Science from FernUniversität in Hagen and Bachelor's degrees from Hochschule Osnabrück and Universidad de Oviedo.