Kyle Mcgill
Senior Systems Software Engineer -AI at NVIDIA
Lake Oswego, Oregon, United States
Summary
🤩
Rockstar🎓
Top SchoolKyle Mcgill is a Senior Systems Software Engineer specializing in AI inference and cloud-native systems, currently contributing to NVIDIA's Triton Inference Server. He brings a 12-year engineering background spanning high-speed trading, production C++ performance work, and full-stack cloud microservices on Kubernetes in Azure. At Rideau Analytics he moved research-grade ML models into low-latency production code and optimized pipelines with Intel VTune, a skillset he now applies to scalable inference and backend/devops tasks. Kyle has practical open-source experience helping maintain code quality and QA for a widely used inference server, and he pairs systems performance instincts with product-focused delivery. Based in Lake Oswego, OR, he blends hands-on implementation with cross-team collaboration across global organizations.
4 years of coding experience
8 years of employment as a software developer
Bachelor of Science (B.S.), Physics, Bachelor of Science (B.S.), Physics at University of California, Santa Barbara
Github Skills (11)
c-language10
cprogramming-language10
testing9
inference9
machine-learning8
bash7
gpu6
dockers5
python5
cloud-computing5
docker5
Programming languages (4)
Github contributions (5)
triton-inference-server/server
Apr 2022 - Dec 2022
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
Role in this project:
Back-end Developer & DevOps Engineer
Back-end Developer & DevOps EngineerContributions:1 release, 393 reviews, 49 commits in 8 months
Contributions summary:Kyle's contributions primarily revolve around code formatting, specifically utilizing clang format to maintain code style consistency across multiple files. They also updated and modified QA tests by incorporating the use of a new max_batch_size feature. Moreover, the user implemented and integrated various features to enhance the overall testing structure and configuration.
inferencegpumachine-learningdeep-learningcloud
nv-kmcgill53/TensorRT-LLM
Sep 2025 - Oct 2025
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and support state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in performant way.
Contributions:6 pushes, 1 branch in 1 month
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.