Matija Teršek
Vice President Of Artificial Intelligence at Luxonis
Ljubljana, Slovenia
Summary
🤩
Rockstar🎓
Top SchoolMatija Teršek is Vice President of Artificial Intelligence at Luxonis, bringing six years of experience building practical computer vision solutions and lightweight neural network architectures. He holds a Master's in Data Science and a background in Computer Science and Mathematics from the University of Ljubljana, blending strong theoretical grounding with hands-on ML engineering. At Luxonis he progressed from ML Engineer to VP, contributing open experimental projects on the DepthAI platform—implementing YOLOv5, DeepLabv3, monocular depth estimation, crowd counting and other applied CV work. He is proficient in PyTorch, Python, R and OOP Java, and has a track record of adapting models and deployment artifacts for embedded and edge environments. Outside work he develops mobile games in Unity and follows state-of-the-art research, reflecting a practical curiosity that informs both product and research efforts. Based in Ljubljana, he’s open to technical conversations spanning ML, CS, math and data science.
6 years of coding experience
6 years of employment as a software developer
Master's degree Data Science, Master's degree Data Science at University of Ljubljana, Faculty of Computer and Information Science
Github Skills (10)
neural-network10
depthai10
computer-vision10
opencv10
machine-learning10
python10
semantic-segmentation9
object-detection9
openvino8
tensorflow6
Programming languages (8)
Github contributions (5)
luxonis/depthai-experiments
Aug 2021 - May 2022
Experimental projects we've done with DepthAI.
Role in this project:
ML Engineer
ML EngineerContributions:17 reviews, 68 commits, 28 PRs in 8 months
Contributions summary:Matija contributed to the development of experimental projects using the DepthAI platform. Their work included implementing and integrating various machine learning models, specifically focusing on computer vision tasks such as semantic segmentation (Deeplabv3 multiclass) and object detection (YOLOv5). The user also added support for different blob files (models) and made adjustments to the codebase for improved performance and compatibility. Additionally, they added experiments for crowd counting, lane detection, text blurring, monocular depth estimation, and face mesh.
deep-learningpythonmachine-learningdepthai
luxonis/depthai-model-zoo
Oct 2021 - May 2022
DepthAI Model Zoo is a collection of open-source neural network models and datasets created and maintained by DepthAI developers and community
Contributions:8 reviews, 67 commits, 27 PRs in 7 months
pytorchdeep-learningmachine-learningnetwork-modelsneural-network
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.