Linas Kondrackis
Open Source Developer at Roboflow
Vilnius, Vilnius County, Lithuania
Summary
🤩
Rockstar🎓
Top SchoolLinas Kondrackis is an open source developer and software engineer with 11 years of professional experience and 15 years of programming practice, specializing in autonomous robotics, computer vision, and ML model deployment. He has built end-to-end vision systems—SLAM, multi-sensor orchestration, depth-camera selection and drivers—and shipped production and simulation work at companies like Dyson and Dynium Robot. Recently pivoting toward entrepreneurship, he’s explored product-market fit through founder-in-residence roles and rapid prototyping of consumer and AI-driven apps. As an active contributor to Roboflow, he maintains and modernizes notebooks and the supervision library, improving object detection, segmentation (SAM), and keypoint inference pipelines. Based in Vilnius, Lithuania, he combines hands-on low-level engineering (camera drivers, sensor networks) with practical product validation and customer research experience.
10 years of coding experience
6 years of employment as a software developer
Bachelor’s Degree, Artificial Intelligence and Computer Science, Bachelor’s Degree, Artificial Intelligence and Computer Science at The University of EdinburghSelf-Driving Car Engineer Nanodegree, Self-Driving Car Engineer Nanodegree at UdacityKaunas University of Technology Gymnasium
English, Lithuanian
Stackoverflow
159reputation
3kreached
9answers
4questions
Github Skills (24)
pytorch10
opencv10
python10
machine-learning10
yolov810
image-segmentation10
segmentation10
computer-vision10
apidoc9
computer-engineering9
api9
deep-learning9
jupyter-notebook9
object-detection8
tensorflow8
Programming languages (8)
Github contributions (5)
roboflow/supervision
Feb 2024 - Jan 2025
We write your reusable computer vision tools. 💜
Role in this project:
Full-stack Developer
Full-stack DeveloperContributions:3 releases, 233 reviews, 189 PRs in 11 months
Contributions summary:Linas primarily contributed to the `supervision/keypoint/core.py` file, implementing a method to create a `KeyPoints` object from inference results, supporting the Roboflow API and the Inference package. They also removed a `class_name` option and incorporated resolution parameters in the inference slicer. Further contributions involved merging updates to the line zone counter, and general code cleanup and minor improvements.
classificationcococomputer-visiondeep-learningimage-processing
roboflow/notebooks
May 2024 - Dec 2024
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
ML EngineerContributions:10 reviews, 41 PRs, 33 pushes in 6 months
Contributions summary:Linas's commits focused on fixing deprecation issues and colors within the `notebooks/how-to-detect-and-count-objects-in-polygon-zone.ipynb` notebook, indicating an effort to maintain code functionality and visual consistency. Further contributions involved using modern supervision 0.23.0 for a SAM (Segment Anything Model) implementation, including notebook metadata updates and library installations, which suggests involvement in computer vision model experimentation. The commits reflect work within the Roboflow notebooks repository, addressing areas like object detection and image segmentation utilizing libraries such as YOLOv8 and OpenCV.
kagglepythonimage-segmentationjupyter-notebookvideos
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.