AI Hardware Test Engineer — Manufacturing & Validation

Amazon Inc.; Austin (TX); On-site; USD 120,000 - 160,000; Full time

Job summary

Annapurna Labs, an AWS organization, is hiring a Manufacturing Test Engineer to develop, deploy, and sustain tests for boards, sleds, and systems in AI training hardware. You will own test development end‑to‑end, from plan to production, and work with hardware, firmware, and software teams across multiple sites.

You will design automated tests, triage failures, and ensure test health as products scale to volume manufacturing, with a focus on quality and reliability in the cloud hardware stack.

Qualifications

• Experience designing and executing test plans for hardware boards, sleds, trays, and systems.
• Designing and building automated test suites and station software.
• Strong programming ability and hands‑on hardware debug skills.
• Ability to triage failures and maintain test health in high‑volume manufacturing.

Responsibilities

• Develop and execute test plans for boards, sleds, trays and systems—from prototype through production.
• Own functional test content for assigned products: device and interface bring‑up, stability under load.
• Design and build automated test suites and station software using Python, C/C++ and shell scripting.
• Deploy tests to manufacturing partners and provide remote triage of failures.
• Drive system‑level and workload‑based functional testing across hardware, firmware and software.
• Debug failures across hardware/firmware boundaries and perform root‑cause analysis.
• Validate tests against known‑good/known‑bad units and ensure production readiness.
• Analyze test and yield data to identify coverage gaps and drive corrective actions.
• Collaborate with contract manufacturers and ODM teams to scale test solutions.

Skills

Python

C/C++

Shell scripting

Test automation

Hardware debugging

Test plans

Job description

Annapurna Labs, an AWS organization, is hiring a Manufacturing Test Engineer to develop, deploy, and sustain tests for boards, sleds, and systems in AI training hardware. You will own test development end‑to‑end, from plan to production, and work with hardware, firmware, and software teams across multiple sites.

You will design automated tests, triage failures, and ensure test health as products scale to volume manufacturing, with a focus on quality and reliability in the cloud hardware stack.