Summary
Andres Delgado is an AI Research Engineer with nine years of experience bridging academic research and applied multimodal vision systems, currently working at Helsing in Munich. He completed a PhD in Computer Vision at UAB and has published at top venues (ECCV, ICCV, WACV, ICDAR), focusing on scene text recognition, cross-modal retrieval, and vision-and-language tasks. His work centers on embedding multi-modal data into common subspaces to enable applications like text-aware image retrieval, fine-grained classification, and VQA, blending deep learning rigor with practical retrieval systems. Past roles include a research internship at NAVER Labs Europe and several industry engineering positions, giving him hands-on experience across research and production contexts. Notably, he combines telecom and data-center engineering roots with advanced computer-vision research, offering a rare mix of systems pragmatism and cutting-edge multimodal modeling.
9 years of coding experience
5 years of employment as a software developer
Doctor of Philosophy - PhD, Computer Vision, Deep Learning, Machine Learning, Doctor of Philosophy - PhD, Computer Vision, Deep Learning, Machine Learning at Universitat Autònoma de Barcelona
Ingeniero en Electrónica y Telecomunicaciones, Ingeniero en Electrónica y Telecomunicaciones at Escuela Politécnica del Ejército
The University of Melbourne
Spanish, English, Catalan