Daniel Bermudez
Beaverton, Oregon, United States
Summary
🤩
Rockstar🎓
Top SchoolDaniel Bermudez is a senior software engineer with a decade of experience specializing in deep learning profilers and tooling at NVIDIA, where he has focused on improving performance analysis and reliability for the widely used Triton Inference Server. He blends systems-level engineering, QA automation, and performance-focused client development—authoring tests, CSV report writers, and stability improvements that make inference pipelines more robust and measurable. Prior roles span chip-design verification, DevOps, and teaching CS labs, giving him a rare mix of hardware-aware thinking and practical software craftsmanship. Based in Beaverton, Oregon, he brings steady delivery from internships to production-grade systems and an eye for testability that surfaces subtle performance regressions before they reach users.
9 years of coding experience
8 years of employment as a software developer
Bachelor's degree, Computer Science, Bachelor's degree, Computer Science at Portland State UniversityMaster of Engineering, Computer Hardware Engineering, Master of Engineering, Computer Hardware Engineering at Cornell University
Github Skills (21)
c-language10
performance-analytics10
performance-monitor10
python10
testing10
bash10
inference10
performance-measurement10
performance-analysis10
performance-tuning10
performance-monitoring10
cprogramming-language10
grpc10
test-automation10
cicd9
Programming languages (3)
Github contributions (5)
triton-inference-server/client
Mar 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 & Performance Engineer
Back-end Developer & Performance EngineerContributions:775 reviews, 13 commits, 160 PRs in 10 months
Contributions summary:Daniel contributed to the client library for Triton Inference Server, focusing on performance analysis and report generation. They developed and updated CSV output features for performance reports, including writing report writers and adding server-side statistics. Additionally, the user made changes to stability formulas and methods within the inference profiler, introducing unit tests and improving the overall performance analysis capabilities of the client. The commits also included adding mocking capabilities and addressing C API segfault fixes.
golangpythongrpcscalaclient-libraries
triton-inference-server/server
Jul 2022 - Aug 2022
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:23 reviews, 4 commits, 16 PRs in 2 months
Contributions summary:Daniel primarily focused on enhancing the quality assurance process for the Triton Inference Server. Their work included adding tests for performance analysis, ensuring correct gRPC time measurements, and implementing unit tests for the Python client. They also introduced tests related to documentation links within the project, thereby contributing to the overall reliability and usability of the server. The user contributed significantly by creating and modifying testing scripts that validate the server's functionality and performance.
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.