Alex Wong
Software Engineer at Amazon
Palo Alto, California, United States
Summary
🤩
Rockstar🎓
Top SchoolAlex Wong is a software engineer in Palo Alto with 11 years of experience building scalable ML systems, distributed infrastructure, and large-scale model deployment pipelines. At Amazon since 2019 he has spanned model training, deployment, and monitoring across Amazon AI and Amazon Music, and his recent focus on deep learning compilers and production ML search systems bridges research-grade models to robust production services. A Cornell CS/ECE graduate (B.S. ’18, M.Eng ’19), he pairs systems-level rigor with hands-on backend and DevOps work—evident in contributions to awslabs/multi-model-server where he improved error handling, testing, and model lifecycle cleanup. He brings hardware-aware perspective from early internships at Intel, Cavium, and Marvell, which informs pragmatic performance and resource optimization decisions in ML infrastructure. Known for shipping reliable production features, he thrives on turning complex model-serving challenges into maintainable, observable systems.
11 years of coding experience
1 year of employment as a software developer
Master's Degree Electrical and Computer Engineering, Master's Degree Electrical and Computer Engineering at Cornell University
Github Skills (15)
javas10
http10
error-handling10
java10
server10
api-design9
restful-api9
testing9
rest-api9
api-rest9
inference8
openapi8
ai8
deeplearning-ai7
deep-learning7
Programming languages (7)
Github contributions (5)
awslabs/multi-model-server
Oct 2019 - Feb 2020
Multi Model Server is a tool for serving neural net models for inference
Role in this project:
Backend & DevOps Engineer
Backend & DevOps EngineerContributions:1 release, 18 commits, 22 PRs in 4 months
Contributions summary:Alex primarily contributed to the backend of the Multi Model Server, specifically focusing on exception handling, and ensuring robust error responses. They implemented new exception types and integrated them into the HTTP request handler, improving the system's error reporting capabilities. Furthermore, the user made changes to the testing framework, adding tests for the conflict scenarios, and updating Open API spec. Moreover, they worked on improving resource cleanup after unregistering models, ensuring models shut down after timeout.
pytorchmxnetservingdeep-learninginference
alexwong/tvm
Nov 2019 - Mar 2021
Open deep learning compiler stack for cpu, gpu and specialized accelerators
Contributions:260 pushes, 24 branches in 1 year 4 months
cpugpu-programminggpu-accelerationtvmdeep-learning
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.