Currently, I am working on Multimodal Retrieval-Augmented Generation (RAG) systems and Vision-Language Models (VLMs). My research interests include urban perception, multimodal large language models (MLLMs), and Explainable AI. I am particularly focused on developing efficient and robust models for analyzing and understanding human perception from street view images, as well as extracting key perceptual features for applications in urban computing.

In addition, I am a PhD candidate at the Escola de Matemática Aplicada (EMAp),  supervised by Prof. Jorge Poco under the CAPES Scholarship. Moreover, I hold a M.Sc. in Computer Science (2020) from the Universidad Católica San Pablo (UCSP), Arequipa, Perú, and a B.Sc. in Computer Science (2017) from the Universidad Nacional de Ingeniería (UNI), Lima, Perú.

Since 2025, I am a DeepLearning AI Mentor in Generative AI with LLMs. In 2018, I was a visiting fellow at the  Royal Academy of Engineering (RAENg), London, UK.