Or Perel

Research Scientist at NVIDIA

Israel
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

🤩
Rockstar
🎓
Top School
Or Perel is a research scientist with 11 years of experience building and optimizing 3D deep learning and computer vision systems, currently at NVIDIA Toronto after prior roles at AWS Rekognition and Autodesk. He blends a strong academic foundation from Tel Aviv University with hands-on engineering across graphics, rendering, and neural fields, contributing back-end improvements to notable open-source projects like NVIDIA Kaolin Wisp. His work focuses on core functionality and performance—refactoring raymarching, interpolation, and acceleration-structure APIs—to make neural field pipelines more robust and efficient. Based in Israel, he brings rare cross-domain expertise from embedded and defense software to large-scale AI research, pairing production-grade engineering with research-driven innovation.
code11 years of coding experience
job13 years of employment as a software developer
bookMaster of Science - MS, Computer Science, Master of Science - MS, Computer Science at Tel Aviv University
bookMamram Graduate (IDF Programming School)
languagesHebrew, English
github-logo-circle

Github Skills (5)

pytorch10
deep-learning10
sdf10
3d10
python9

Programming languages (2)

TypeScriptPython

Github contributions (5)

github-logo-circle
NVIDIAGameWorks/kaolin-wisp

Aug 2022 - Jan 2023

NVIDIA Kaolin Wisp is a PyTorch library powered by NVIDIA Kaolin Core to work with neural fields (including NeRFs, NGLOD, instant-ngp and VQAD).
Role in this project:
userBack-end Developer
Contributions:2 releases, 7 reviews, 38 commits in 5 months
Contributions summary:Or primarily contributed to the `nvidiagameworks/kaolin-wisp` repository by modifying and refining existing code within the project. The commits focused on fixing indentation issues, adding default color options for sparse point clouds (SPCs), and refactoring the raymarching and interpolation output to streamline the SDF pipeline. The user also updated the API for grids and acceleration structures. These changes focused on core functionality and optimization of the library.
nvidiapytorch3d-deep-learningnerfsdf
orperel/LaplacianMeshEditing

Jan 2020 - Mar 2022

Contributions:25 commits in 2 years 2 months
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