Uros Durdevic is a founder and product-focused engineer with a decade of experience designing and building mobile and web products, currently scaling Luckynote — a personal-knowledge app used by thousands across iOS, Android and desktop. His background blends hands-on frontend development (Angular, React Native) and UX/product design from roles at medzapp, SportJoe, CheMondis and epilot, enabling him to turn fuzzy user needs into polished, usable experiences. He also contributes to ML projects on GitHub, improving facial-landmark detection implementations by refining training pipelines and fixing model bugs, showing a comfort with both product and applied machine learning. Based in Germany and self-described as someone who builds tools to remember why things mattered, he brings founder-level ownership together with practical engineering chops and a bias for shipping.
10 years of coding experience
8 years of employment as a software developer
Bachelor's degree, Bachelor's degree at University of Belgrade
Implementation of PFLD A Practical Facial Landmark Detector , reference to https://arxiv.org/pdf/1902.10859.pdf
Role in this project:
ML Engineer
Contributions:14 commits, 4 PRs, 34 comments in 1 month
Contributions summary:Uros primarily contributes to the implementation and refinement of a facial landmark detector. Their work includes adding code for computing Euler angles, fixing bugs in the running model, and updating the training model. The user is involved in integrating with external datasets and defining the training process. These contributions center around improving the model's functionality and potentially improving its accuracy in determining facial landmarks.
Contributions:14 commits, 10 pushes, 1 branch in 1 month
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.