Drimva

Amazon

Software Development Engineer II, Post Silicon Validation

$144K–$194K

Austin, TX · Full-time · Posted Sep 10, 2026

Experience
3+ years of non-internship professional software development; 2+ years of non-internship design or architecture of new and existing systems; 3+ years of hands-on post-silicon validation or system validation engineering. Preferred: 3+ years of full software development life cycle experience.
Education
Bachelor's degree in computer science or equivalent (preferred).

About the job

Validates machine-learning accelerator hardware and software from early design through silicon bring-up and production support in AWS data centers.

What you'll do

  • Develop and execute validation strategies and test plans across simulation, emulation, silicon bring-up, and product release.
  • Debug hardware and software issues in the lab, validate accelerator performance with neural-network workloads, and build automated test infrastructure.
  • Collaborate across architecture, design, firmware, and software teams to resolve failures and support deployed systems.

What they ask for

  • At least one software programming language; strong programming skills for production-quality test code.
  • 3+ years of hands-on post-silicon validation or system validation engineering experience.
  • Experience developing and executing validation test plans for complex SoCs, CPUs, or accelerators; hands-on hardware bring-up and debug experience.
  • Understanding of computer architecture and digital design principles; proficiency with Linux, Git, and SSH.

Nice to have

  • Bachelor's degree in computer science or equivalent.
  • Experience with AWS or cloud technologies, automated test frameworks and CI/CD, PCIe or HBM, ML hardware, emulation, firmware, or EDA simulation tools.

Pay

143,700.00 - 194,400.00 USD annually (base salary)

Tools

Python, Lua, C/C++, Rust, Linux, Git, SSH, AWS

AI focus

Validates next-generation machine-learning accelerators, including their performance, accuracy, and reliability on neural-network workloads.

Model-written summary · the original posting is authoritative

First seen Oct 15, 2026 · Last verified Nov 4, 2026 (UTC)