Piotr Skalski is an Open Source Lead and computer vision engineer with nine years of experience building tooling, tutorials, and production systems for ML and CV. He founded makesense.ai, an open-source image labelling tool used by thousands daily and star-rated on GitHub, and helped create Roboflow’s Supervision library and Notebooks that power hundreds of public projects and tutorials. A prolific educator, Piotr reaches a wide audience through a Medium post on coding neural nets in NumPy that drew over 250k readers and regular Roboflow video content. His contributions span front-end UI for annotation tools to core object-detection utilities and YOLOv5 improvements, showing fluency across full-stack and model-level work. Comfortable taking models from research to edge deployment, he has optimized and benchmarked CV solutions for production and industrial use. Based in Krakow, he blends practical engineering with community-driven open-source impact and a knack for turning complex CV concepts into approachable tutorials and tools.
9 years of coding experience
9 years of employment as a software developer
Master's degree Civil engineering, Master's degree Civil engineering at Politechnika Krakowska im. Tadeusza Kościuszki
Computer Science, Computer Science at AGH University of Krakow
This repository offers a comprehensive collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-edge models like YOLO11, RT-DETR, SAM 2, Florence-2, PaliGemma 2, and Qwen2.5VL.
Role in this project:
ML Engineer
Contributions:1 release, 40 reviews, 136 commits in 3 months
Contributions summary:Piotr's commits primarily focus on the development and implementation of a training notebook utilizing YOLOv12 for object detection on a custom dataset. Their contributions involve defining image processing pipelines, creating annotations, and establishing datasets for training and evaluation. The user demonstrates a strong understanding of object detection frameworks.
Contributions:19 releases, 509 reviews, 103 commits in 3 months
Contributions summary:Piotr appears to have made significant contributions to the project, initially setting up the foundational structure by implementing essential classes and tools, including color palettes, geometric primitives, and video handling utilities. Subsequent commits demonstrate active involvement in feature development with the addition of core object detection functionalities, including classes for detections and annotation with bounding boxes. The user also maintained documentation and expanded the toolset.
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.