Sabosan Tech
Software Engineer
Summary
🤩
RockstarSabosan Tech is a software engineer with four years of hands-on experience focusing on practical ML engineering and model integration. He has contributed to the axinc-ai/ailia-models repository, improving Movenet pose-estimation usability by fixing image type conversions, correcting output image handling, and refining preprocessing/postprocessing—changes that moved the code away from brittle Matplotlib dependencies. Comfortable bridging research models and production SDKs, he emphasizes robustness and reproducible image pipelines. Though early in his career, Sabosan demonstrates attention to detail that reduces friction for downstream users of open-source ML tools.
4 years of coding experience
Github Skills (8)
computer-vision10
machine-learning10
opencv10
python10
pose-estimation10
image-processing9
neural-network9
matplotlib6
Programming languages (1)
Github contributions (5)
axinc-ai/ailia-models
Aug 2021 - Oct 2021
The collection of pre-trained, state-of-the-art AI models for ailia SDK
Role in this project:
ML Engineer
ML EngineerContributions:5 commits, 2 PRs, 2 pushes in 2 months
Contributions summary:Sabosan primarily contributed to the `pose_estimation/movenet` module within the repository, focusing on enhancing the model's usability. Their work included fixing an image type conversion issue to allow for saving processed images, and correcting the method used for obtaining the output image, which was previously erroneously dependent on Matplotlib. They also made adjustments for accurate image preprocessing and postprocessing for pose estimation.
image-segmentationface-recognitionhand-detectionstate-of-the-artimage-classification
sabosantech/check_account
Aug 2021 - Aug 2021
Contributions:1 push, 1 branch in 1 day
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.