David Goodwin

United States

Join Prog.AI to see contacts

Summary

🤩

Rockstar

🎓

Top School

David Goodwin is a seasoned engineering leader and hands-on individual contributor with over a decade building high-performance inference and delivery systems, most notably as architect and development lead for NVIDIA's Triton Inference Server. He combines deep hardware and software expertise—from low-level APIs and binary data handling to scalable GRPC/HTTP clients and CI improvements—with a track record of shipping production-ready ML infrastructure. His work on Triton’s client and server components shows a focus on performance, maintainability, and observability (including correlation IDs and streaming async calls). Prior roles at Apple, Tensilica, and startups demonstrate an ability to bridge research-grade systems and commercial products. He holds a Ph.D. in Computer Science and a B.S. in Electrical Engineering, bringing both academic rigor and pragmatic engineering to cross-functional teams.

10 years of coding experience

16 years of employment as a software developer

Ph.D., Computer Science, Ph.D., Computer Science at University of California, Davis

B.S., Electrical Engineering, B.S., Electrical Engineering at Virginia Tech

Github Skills (11)

http10

c-language10

api10

cprogramming-language10

apidoc10

grpc10

server-client9

client-server9

performance-optimization9

testing8

tensorflow6

Programming languages (8)

TypeScriptC++CGoHTMLJupyter NotebookJsonnetPython

Github contributions (5)

triton-inference-server/server

Oct 2018 - Apr 2022

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

Role in this project:

Back-end Developer & DevOps Engineer

Contributions:10 releases, 1297 reviews, 1183 commits in 3 years 6 months

Contributions summary:David's contributions focused on improving the client-side implementations, specifically the simple and sequence GRPC client, by ensuring the use of streaming with async calls. Furthermore, the user made improvements to the low-level API and the client to support binary data output. They also added a model repository and improved the CI tests to ensure all model instance are ready. These changes, along with updates to logging, indicate contributions to performance and maintainability.

nvidia-dockernvidiadeep-learninggpuinference

triton-inference-server/client

Nov 2018 - Mar 2022

Triton Python, C++ and Java client libraries, and GRPC-generated client examples for go, java and scala.

Role in this project:

Back-end Developer

Contributions:81 reviews, 157 commits, 29 PRs in 3 years 4 months

Contributions summary:David's contributions primarily focused on modifying the GRPC API to use int32 for model versions. They also removed unnecessary verbose output in a performance client, indicating a focus on code optimization. Further, they addressed string data types for tensors, adding string support and implementing fixes for string type outputs for HTTP API. The user added correlation ID features to the inference API and client, enhancing the API.

golangpythongrpcscalaclient-libraries

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.

Request Free Trial