Edgar Riba
Staff Research Engineer at Bonsai Robotics
Barcelona, Catalonia, Spain
Summary
🤩
Rockstar🎓
Top SchoolEdgar Riba is a Staff Research Engineer and co-founder of Kornia with 12 years of experience applying geometric computer vision and deep learning to robotics and spatial AI. He holds a PhD in Computer Vision and combines research rigor with hands-on engineering—contributing to flagship open-source projects like OpenCV (notably solvePnPRansac and SfM modules) and developing core image-processing operators in Kornia. Currently building foundational models, datasets, and research tools for robotics at Bonsai Robotics, he has a proven track record of shipping both C++ core library work and PyTorch-based ML components. His career spans academic research, industry R&D, and startup leadership, bridging low-level algorithmic improvements and practical ML tooling for production. An unassuming thread across his work is a focus on reproducible open-source code: from integrating tiny-dnn into OpenCV to creating Kornia as a differentiable vision library. Based in Barcelona, he’s open to collaborations that push spatial AI into real-world robotic systems.
12 years of coding experience
8 years of employment as a software developer
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at Universitat Autònoma de BarcelonaUPC Universitat Politècnica de CatalunyaUOC (Universitat Oberta de Catalunya)
Catalan, English, Spanish
Stackoverflow
41reputation
10kreached
1answer
1question
Github Skills (38)
algorithm10
pcl10
algorithms10
pytorch10
opencv10
c-language10
python10
operation10
ransac10
image-processing10
classification10
image-classification10
tensorrt10
machine-learning10
image-filters10
Programming languages (16)
Github contributions (5)
kornia/kornia
Aug 2018 - Jan 2023
🐍 Geometric Computer Vision Library for Spatial AI
Role in this project:
ML Engineer
ML EngineerContributions:35 releases, 2445 reviews, 2264 commits in 4 years 5 months
Contributions summary:Edgar implemented and integrated Sobel edge detection operators and box blur filters, along with a new median blur filter. They added and tested these image processing algorithms within the Kornia framework, expanding its image filtering capabilities. Furthermore, the user refactored existing code, including renaming functions and updating documentation to improve clarity and consistency within the library. The user focused on image processing tools.
pytorchdifferentiablepythonvisiondeep-learning
tiny-dnn/tiny-dnn
May 2016 - Aug 2018
header only, dependency-free deep learning framework in C++14
Role in this project:Back-end Developer
Back-end DeveloperContributions:96 commits, 263 PRs, 185 pushes in 2 years 3 months
Contributions summary:Edgar made commits focused on refactoring the internal structure of the `tiny-dnn` project, particularly within the layer implementation. These changes included modifying data accessors, enhancing the Tensor class with move semantics, and implementing element-wise operations like addition, subtraction, multiplication, and division, indicating an emphasis on core functionality and performance. These updates involved adjustments to the layer class, potentially improving data handling, and optimizing existing code through refactoring.
cppheaderdeep-learningc-plus-plusmachine-learning
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.