Stella Liu is a specialist and researcher in the field of AI evaluation (AI Evals), specializing in the development of evaluation methodologies for large language models and AI products.
Since 2023, she has been leading practical projects on AI system evaluation. Stella developed one of the first comprehensive evaluation frameworks for AI products in the higher education sector and continues to engage in research on the safe and responsible application of AI. In her work, she combines practical experience in product creation and evaluation with an academic approach, adapting modern AI Evals methods for corporate and educational tasks.
Before working in the education field, Stella worked at Shopify and Carvana, where she was involved in creating data-driven systems that helped improve digital products, automate processes, and enhance operational efficiency in large-scale companies.