Sam Karu
Co-founder & CEO at Logical (YC F25)
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolSamurdhi Karunaratne is a Software Engineer based in California with four years of experience focused on deep learning inference. Currently contributing at NVIDIA, he works on TensorRT—an industry-leading SDK for high-performance inference—where he fixes integration bugs, enables plugin attribute tests, and resolves stability issues like segfaults and Windows hang-ups when importing TensorFlow. His hands-on contributions indicate strong expertise in plugin implementation, cross-library interoperability, and productionizing ML inferencing on GPUs. Comfortable digging into low-level debugging and CI/configuration details, he bridges the gap between research frameworks and reliable deployment. Colleagues rely on him for making complex inference stacks more robust and maintainable.
4 years of coding experience
6 years of employment as a software developer
Bachelor of Science (BSc) Computer Engineering, Bachelor of Science (BSc) Computer Engineering at University of PeradeniyaUniversity of California, Los Angeles
English, Sinhalese, Tamil
Github Skills (9)
tensorrt10
deep-learning10
inference10
gpu-acceleration10
cprogramming-language9
c-language9
plugin-development9
python8
cuda7
Programming languages (2)
Github contributions (5)
NVIDIA/TensorRT
Jan 2022 - Dec 2022
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
Role in this project:
ML Engineer
ML EngineerContributions:17 reviews, 12 commits, 31 PRs in 10 months
Contributions summary:Sam primarily contributes to the NVIDIA TensorRT repository, a deep learning inference SDK. Their work focuses on addressing bugs related to TensorFlow integration with TensorRT, specifically resolving hanging issues on Windows when importing TensorFlow after TensorRT. Additionally, the user has added configuration files and enabled attribute tests for various plugins within the TensorRT ecosystem, and also fixed a segfault within the Normalize plugin. This indicates a strong involvement in maintaining and improving the functionality and stability of the TensorRT library, particularly related to plugin implementation.
deep-learning-inferencenvidiadeep-learningruntimeinference
samurdhikaru/TensorRT
Jun 2023 - Sep 2024
Contributions:9 pushes, 12 branches in 1 year 3 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.