Lojze Žust
Research Scientist at University of Ljubljana, Faculty of Computer and Information Science
Grenoble, Auvergne-Rhône-Alpes, France
Summary
👤
Senior🎓
Top SchoolLojze Žust is a research scientist and PhD student in computer vision with a decade of software and research experience spanning autonomous marine perception, earth observation, and deep learning. He combines strong Python and PyTorch/TensorFlow skills with practical ML engineering—contributing to the widely used eo-learn framework on cloud masking and image resizing—and has applied those skills at NAVER LABS Europe, Sinergise, and Stanford. His doctoral work focuses on vision-based obstacle detection for autonomous boats, reflecting a blend of applied robotics and remote sensing expertise. Known for an analytical mindset and meticulous attention to detail, he moves smoothly between prototyping research methods and production-focused code refactors. Notably, his contributions to multi-temporal cloud detection demonstrate an uncommon ability to bridge algorithmic research with real-world Earth observation pipelines.
10 years of coding experience
6 years of employment as a software developer
Master's degree, Computer Science, 9,7/10, Master's degree, Computer Science, 9,7/10 at University of Ljubljana, Faculty of Computer and Information ScienceHigh School, Classical Gymnasium, Matura: 32 points, High School, Classical Gymnasium, Matura: 32 points at Diocesan Classical Gymnasium
English, Slovenian
Stackoverflow
13reputation
2kreached
0answers
2questions
Github Skills (10)
computer-vision10
machine-learning10
python10
image-processing10
numpy10
opencv9
recursion6
keras6
tensorflow6
forloop6
Programming languages (4)
Github contributions (5)
sentinel-hub/eo-learn
Jul 2019 - Oct 2019
Earth observation processing framework for machine learning in Python
Role in this project:
ML Engineer
ML EngineerContributions:51 commits, 3 PRs, 31 comments in 2 months
Contributions summary:Lojze contributed significantly to the `eo-learn` framework, focusing on cloud masking and image resizing functionalities. Their work involved implementing and refining the `AddMultiCloudMaskTask`, which integrates mono-temporal and multi-temporal cloud detection classifiers. They addressed bugs, optimized code, and refactored utilities, specifically related to image processing and resizing within the context of Earth observation data.
earth-observationmachine-learningpythoneo-dataeo-research
sentinel-hub/eo-flow
Sep 2019 - Mar 2020
Collection of TensorFlow 2.0 code for Earth Observation applications
Contributions:162 commits, 18 PRs, 53 pushes in 5 months
earth-observationtensorflow
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.