Summary
Abdelrahman Eldesokey is a postdoctoral researcher at KAUST with eight years of experience advancing generative AI and computer vision, specializing in diffusion models, vision foundation models, and multimodal large language models. He bridges perception and creation by developing systems that both understand and generate visual content, with deep expertise in detection, segmentation, tracking, video analysis, depth and LiDAR-based vision. His background spans academic research (PhD in Computer Vision from Linköping University) and industry roles including senior ML engineering at Signality, giving him a strong track record of moving ideas from research to applied systems. He also explores uncertainty estimation and AI for sports, an indication of his interest in real-world, high-impact applications beyond core modeling. Notably, his work blends theoretical rigor with practical deployment experience across robotics, video, and multimodal understanding.
8 years of coding experience
4 years of employment as a software developer
Bachelor of Science (BS), Computer Engineering, Bachelor of Science (BS), Computer Engineering at Mansoura University
Thanwya Amma, Thanwya Amma at Al Hoda wal Nour private schools
Master of Science (MSc), Informatics, 3.97, Master of Science (MSc), Informatics, 3.97 at Nile University - NU
Doctor of Philosophy - PhD, Computer Vision, Doctor of Philosophy - PhD, Computer Vision at Linköping University
Swedish, English, Arabic