Post-Silicon ML Accelerator Validation Engineer

Amazon Web Services (AWS); Austin (TX); On-site; USD 144,000 - 194,000; Full time

Job summary

Annapurna Labs (U.S.) Inc. in Austin seeks a skilled Silicon Validation Engineer to validate next-generation ML accelerators powering AWS infrastructure.

You will join a fast-paced, startup-like environment and work across silicon, PCB, high-speed interfaces, and software to deliver reliable hardware and software products. Responsibilities include developing validation strategies, executing tests from RTL to silicon, hands-on bring-up with lab equipment, and building CI/CD pipelines to enable

Qualifications

• 3+ years of non-internship design or architecture experience
• Experience with Machine Learning and ML fundamentals, or PyTorch/JAX experience
• Bachelor's degree or equivalent in CS/engineering/math

Responsibilities

• Developing validation strategies and detailed test plans from silicon bring-up to product release
• Executing complex test plans from RTL simulation and emulation to silicon validation
• Hands-on silicon bring-up and debug in lab with oscilloscopes and protocol analyzers
• Validating ML accelerator performance, accuracy and reliability on real workloads
• Building CI/CD pipelines and automated regression for scalable validation

Skills

Python

C/C++

Rust

Go

Computer architecture

ML fundamentals

CI/CD

Debugging

Education

Bachelor's degree in Computer Science or related field

Tools

SystemVerilog/UVM

VCS

Questa

Xcelium

Palladium

Zebu

Veloce

Job description

Annapurna Labs (U.S.) Inc. in Austin seeks a skilled Silicon Validation Engineer to validate next-generation ML accelerators powering AWS infrastructure.

You will join a fast-paced, startup-like environment and work across silicon, PCB, high-speed interfaces, and software to deliver reliable hardware and software products. Responsibilities include developing validation strategies, executing tests from RTL to silicon, hands-on bring-up with lab equipment, and building CI/CD pipelines to enable