Nick Comly
San Francisco, California, United States
Summary
🤩
RockstarNick Comly is a Product Manager based in San Francisco with four years of experience focused on AI inference tooling, currently working on TensorRT at NVIDIA. He combines product strategy with hands-on technical understanding of ML deployment, helping teams bridge model performance and production constraints. Colleagues would describe him as pragmatic and data-driven, prioritizing measurable improvements in latency and throughput. Though early in his career, he brings concentrated domain expertise in GPU-accelerated inference and a track record of shipping features that matter to ML engineers.
5 years of coding experience
Github Skills (19)
torchscript10
pytorch10
runtimes10
jetson10
python10
tensorrt10
machine-learning10
inference10
large-language-models10
llm10
nvidia10
libtorch10
deep-learning10
cuda10
cpp10
Programming languages (3)
Github contributions (5)
ncomly-nvidia/TensorRT-LLM
Apr 2025 - Jan 2026
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
Contributions:8 pushes in 9 months
ncomly-nvidia/TRTorch
Aug 2021 - Aug 2021
PyTorch/TorchScript compiler for NVIDIA GPUs using TensorRT
Contributions:2 pushes in 1 day
compilernvidiapytorchtensorrttorchscript
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.