Onur Kaplan

ML Research Engineer at Miletos Inc.

Istanbul, Istanbul, Turkey
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

👤
Senior
🎓
Top School
Onur Kaplan is an ML Research Engineer with 11 years of experience building production-ready machine learning and computer vision solutions from Istanbul. Currently at Miletos Inc., he combines a strong electrical and electronics engineering foundation from Istanbul Technical University with hands-on expertise in PyTorch and geometric computer vision. Notably, he contributed JIT-compatibility improvements to the widely used Kornia library—implementing and testing warp perspective and affine transforms and addressing tooling and testing issues. He excels at bridging research and engineering, simplifying complex models for robust deployment and tooling compliance. Colleagues describe him as a pragmatic problem-solver who values clean, testable code and reproducible ML workflows.
code11 years of coding experience
bookBachelor's degree, Electrical, Electronics and Communications Engineering, Bachelor's degree, Electrical, Electronics and Communications Engineering at Istanbul Technical University
github-logo-circle

Github Skills (9)

computer-vision10
pytorch10
deeplearning-ai10
deep-learning10
jit10
python9
neural-network9
image-processing8
machine-learning7

Programming languages (1)

Python

Github contributions (5)

github-logo-circle
kornia/kornia

Jan 2019 - Jan 2019

🐍 Geometric Computer Vision Library for Spatial AI
Role in this project:
userML Engineer
Contributions:8 commits, 3 PRs, 8 comments in 3 days
Contributions summary:Onur's contributions primarily focused on making the `kornia` library jit-compatible, involving modifications to support PyTorch's JIT compiler. They implemented and tested features related to geometric computer vision, including warp perspectives and affine transformations. The user also debugged flake8 warnings and simplified the model used in the tests. Their work demonstrates an understanding of PyTorch, computer vision, and the requirements for JIT compatibility.
pytorchdifferentiablepythonvisiondeep-learning
Wizaron/reseg-pytorch

Dec 2017 - Jan 2018

Contributions:30 commits, 24 pushes, 1 branch in 29 days
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.
Request Free Trial
Onur Kaplan - ML Research Engineer at Miletos Inc.