Software Development Engineer, CV Test Infrastructure - Annapurna ML

Are you passionate about building the infrastructure that powers next-generation AI/ML hardware? Do you want to work at the intersection of software engineering and chip development, enabling teams to validate cutting-edge silicon at scale?
Amazon's Annapurna ML organization is looking for a Software Development Engineer to join our CV Test Infrastructure team. In this role, you'll build and maintain the automated validation infrastructure that enables chip verification and validation across multiple engineering teams and hardware platforms. You'll work on our Origami platform — a web-based and desktop system for test management, resource monitoring, and validation reporting — and develop automation that spans emulators (ZeBu), virtual platforms (QEMU), and silicon prototypes.
This is a high-impact role where your work directly accelerates the development of custom AI/ML chips powering AWS services used by millions of customers worldwide.


Key job responsibilities
- Design, develop, and maintain automation frameworks for test execution across emulation, virtual platform, and silicon environments
- Build and enhance CI/CD pipelines for nightly regression and on-demand test execution
- Develop and improve the Origami platform for test management, resource monitoring, and validation reporting
- Automate emulator model build and release processes
- Build dashboards and tooling for real-time visibility into regression results, resource utilization, and test coverage
- Collaborate with hardware and software verification teams to understand testing needs and deliver scalable solutions


A day in the life
You'll start your day reviewing overnight regression results, triaging infrastructure issues, and unblocking engineering teams. You might spend the morning improving a CI/CD pipeline to reduce build times, then shift to developing a new feature in the Origami platform that gives engineers better visibility into test coverage. You'll collaborate closely with verification engineers, firmware developers, and other infrastructure teams to ensure our validation systems keep pace with the rapid cadence of chip development.

About the team
Annapurna Labs is a wholly owned subsidiary of AWS, focused on developing custom silicon and servers including the Nitro, Graviton, Inferentia, and Trainium families of processors.
Machine Learning Annapurna (MLA) functions as a vertically integrated team including software, firmware, hardware, and silicon design in a single organization.
We are the Training Servers and Systems organization under MLA focused on Hardware Development, Software Development, Fleet Ops Systems, and Manufacturing, Quality, and Reliability.
This position is in the Manufacturing, Quality and Reliability team.