Researching approaches to evaluate LLMs and RAG systems (among others) for trustworthiness (performance, bias, safety, robustness, etc). About me: - Former Applied science intern in the Alexa AI team at Amazon, working on dialogue response generation and dialogue act tagging (NLP). - Master's graduate at Universite de Montreal (MILA research group), specialising in machine learning. - Several years of experience as a software engineer.