I’m a Machine Learning Scientist specialising in computer vision and deep learning, with a PhD in Artificial Intelligence from the University of Leeds, completed under the supervision of Prof. David Hogg. My background began in software engineering, where I worked on real-world systems ranging from web applications to computer vision and OCR pipelines, before transitioning fully into research. My recent work focuses on foundation models, self-supervised learning, and multimodal vision systems, particularly for earth observation and space applications. I currently work at Hydrosat developing computer vision models for satellite imagery, and I’ve previously held research roles at the University of Luxembourg and the University of Leeds. I’ve published multiple peer-reviewed research works and actively contribute to the community through reviewing, mentoring, and volunteering, including supporting workshops and initiatives for LatinX in Computer Vision @ CVPR 2024 and 2025.

Paper: https://arxiv.org/pdf/2602.17799

Code: https://github.com/josesosajs/trainfree-rs-segmentation

Paper: https://arxiv.org/abs/2602.04699

Code: https://github.com/giddyyupp/annotation-free-spacecraft-segmentation

Paper: https://arxiv.org/abs/2505.14951

Code: https://github.com/josesosajs/multimae-meets-eo

Presentation: https://www.youtube.com/watch?v=GR7iAT5u9P8

Paper: http://arxiv.org/abs/2509.06000