Matthew Kotila
Software Engineer - Deep Learning Tools at NVIDIA
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolMatthew Kotila is a software engineer specializing in deep learning tools with 11 years of experience building and hardening inference infrastructure at NVIDIA from intern to full-time engineer. He combines backend systems and QA/test-automation expertise—contributing to the Triton Inference Server by enhancing performance analyzer clients, adding SSL support for gRPC/HTTP, and improving GPU metrics and test coverage. Comfortable across languages and environments, he has a research background in ML (polynomial regression vs. neural nets), practical experience at national labs and Apple, and a teaching history that emphasizes first-principles reasoning. Based in San Francisco with MS and BS degrees from UC Davis, he brings a blend of production-grade engineering, rigorous testing, and an appreciation for expressive, story-driven code.
11 years of coding experience
1 year of employment as a software developer
Bachelor of Science - BS, Computer Science, Bachelor of Science - BS, Computer Science at University of California, Davis
Github Skills (24)
c-language10
http10
bash10
inference10
performance-testing10
triton10
performance-analysis10
triton-server10
cprogramming-language10
grpc10
test-automation10
ssl9
command-line-interface9
tls129
tls139
Programming languages (6)
Github contributions (5)
triton-inference-server/client
Feb 2022 - Jan 2023
Triton Python, C++ and Java client libraries, and GRPC-generated client examples for go, java and scala.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:1060 reviews, 26 commits, 182 PRs in 11 months
Contributions summary:Matthew primarily focused on enhancing the performance analyzer (PA) client libraries within the Triton Inference Server. Their contributions involved implementing and refining SSL options for gRPC and HTTP communication, specifically within the C++ client. The user added new command-line options to the PA tool related to SSL, enabling users to configure secure connections. Furthermore, the user refactored the code to include GPU metrics for server side stats.
golangpythongrpcscalaclient-libraries
triton-inference-server/server
Jan 2022 - Jan 2023
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
Role in this project:QA Engineer / Test Automation Engineer
QA Engineer / Test Automation EngineerContributions:65 reviews, 11 commits, 39 PRs in 1 year
Contributions summary:Matthew's contributions center around enhancing the testing framework for the Triton Inference Server. Their work includes implementing tests for secure gRPC and HTTP protocols, specifically using SSL. The user also added and improved performance analyzer tests, including multi-model and optional input testing. Furthermore, they've created and maintained unit tests for the performance analyzer, demonstrating a strong focus on test coverage and reliability of the project.
nvidia-dockernvidiadeep-learninggpuinference
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.