Michael W
Sr Software Development Manager - AWS Neuron SDK - Trainium And Inferentia at Amazon Web Services (AWS)
Seattle, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolMichael W is a senior software development manager with 20+ years of systems and hardware-software co-design experience, currently leading the AWS Neuron SDK for Trainium and Inferentia to bring cloud-scale ML acceleration to production. He has a proven track record shipping high-impact infrastructure and silicon-adjacent software—delivering Inferentia/Trainium runtimes, drivers, and tooling at AWS and previously driving network and storage performance breakthroughs for EC2. Michael blends hands-on ML engineering (notably benchmarking PyTorch BERT on Inferentia via the aws-neuron-sdk) with strategic product leadership across teams at AWS and Intel. Comfortable moving between low-level performance optimization and customer-facing service launches, he repeatedly turns complex architecture challenges into scalable, market-ready solutions. Based in Seattle, he pairs an MS in Computer Science with experience founding an aerospace ML startup, reflecting both deep technical chops and entrepreneurial curiosity.
6 years of coding experience
9 years of employment as a software developer
Master of Science (M.S.), Computer Science, Master of Science (M.S.), Computer Science at The University of Tennessee at ChattanoogaBachelor of Science (B.S.), Computer Science, Bachelor of Science (B.S.), Computer Science at Hiram College
Github Skills (9)
pytorch10
machine-learning10
performance-optimization10
compilation10
bert10
compile10
aws9
classification9
sequence-labeling9
Programming languages (4)
Github contributions (5)
aws-neuron/aws-neuron-sdk
Dec 2019 - Aug 2021
Powering AWS purpose-built machine learning chips. Blazing fast and cost effective, natively integrated into PyTorch and TensorFlow and integrated with your favorite AWS services
Role in this project:
ML Engineer
ML EngineerContributions:2 releases, 17 reviews, 97 commits in 1 year 8 months
Contributions summary:Michael's commits focus on adapting and demonstrating the performance of PyTorch BERT models on Inferentia hardware. They are creating and running benchmark scripts to assess accuracy, latency, and throughput. This includes setting up and benchmarking a PyTorch BERT model for MRPC sequence classification, as well as developing a performance test for the compiled model. Their work leverages PyTorch and the Neuron SDK to optimize model execution on specialized hardware.
pythoncost-effectivetensorflowawsintegrated
micwade-aws/micwade-aws
Jul 2020 - Jun 2022
Contributions:1 push, 1 branch in 1 year 11 months
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.