Matteo Bortolon is a PhD student at Istituto Italiano di Tecnologia and Fondazione Bruno Kessler, specializing in computer vision and 3D reconstruction with eight years of experience spanning academia and software development. His research includes a transformer-based model for real-time visual relocalization in PyTorch achieving 18 FPS and a 22% accuracy/speed improvement over industry benchmarks, trained on as few as 150 images across indoor, outdoor, and object-centric scenarios. He also developed NeRF-based and Gaussian Splatting 3D reconstruction methods that produce high-quality models from as few as four images, maintaining strong accuracy on standard benchmarks. In parallel, he has built production software such as a GRAV-based PHP/Symfony website builder used for numerous events, and he led infrastructure optimizations delivering up to 90% cost reductions and 20% faster load times. He has shipped a real-time 3D human modeling app—built with Unity (C#/C++), FastAPI and Rust, and deployed on edge Kubernetes/AWS—for live pose estimation and body reconstruction. Based in Altivole, Italy, Matteo combines hands-on software engineering with cutting-edge ML research, making him a versatile contributor to both research and production teams.
8 years of coding experience
1 year of employment as a software developer
Diploma, Informatica, 91/100, Diploma, Informatica, 91/100 at ITT E. Barsanti
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at Università di Trento
Bachelor of Engineering - BE, Information and Business Organisation Engineering, 104 out of 110, Bachelor of Engineering - BE, Information and Business Organisation Engineering, 104 out of 110 at University of Trento
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.