I am a recent PhD graduate in Computer Science specializing in Trustworthy and Responsible AI. My research sits at the intersection of explainable AI, federated learning, multimodal systems, and AI for healthcare.
My doctoral work focused on developing privacy-preserving and interpretable deep learning frameworks for medical decision support, particularly for acute lymphoblastic leukemia diagnosis. I work on making foundation models and multimodal systems more robust, transparent, and safe for high-stakes domains such as healthcare, robotics, and autonomous systems.
I publish regularly on these topics and am interested in contributing to research groups working on reliable multimodal foundation models that can adapt safely to new environments while maintaining robustness and calibrated confidence.
📍 Based in Portugal 🔗 Google Scholar | ORCID: 0009-0007-6971-8140
