Summary
Oscar Mañas is a research scientist specializing in multimodal vision-and-language models, with a decade of experience spanning academic and industry labs. Currently a Research Scientist at Meta and a PhD candidate at Mila/Université de Montréal, he has a track record of internships and collaborations across Meta FAIR, Element AI, and leading vision research groups in Europe. His work emphasizes data-efficient and self-supervised visual representations that bridge computer vision and NLP, informed by applied projects in real-time video analysis and edge-efficient neural networks. Known for combining rigorous academic training (top grades in MS and BS programs) with practical engineering—shipping prototypes for sports production and real-estate visual recognition—he brings both experimental depth and production sensibility. Based in Zurich, he often operates at the nexus of research and deployment, unusually fluent in turning theoretical multimodal ideas into scalable systems.
11 years of coding experience
6 years of employment as a software developer
Master of Science - MS, Computer Vision, 9.58/10, Master of Science - MS, Computer Vision, 9.58/10 at Universitat Autònoma de Barcelona
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at Université de Montréal
UPC Universitat Politècnica de Catalunya
Spanish, Catalan, English, French