Senior Cloud AI Accelerator GPU Engineer

Amazon; Cupertino (CA); On-site; USD 183,000 - 248,000; Full time

Benefits offered by this job

Health insurance

401(k) matching

Paid time off

RSUs

Adoption and Surrogacy reimbursement

Job summary

Amazon in Cupertino is seeking a Senior Hardware Development Engineer to own the GPU lifecycle, from hardware and firmware requirements through qualification, field operations, and fleet-scale deployment. You will be the single-threaded owner of GPU lifecycle, translating fleet data into vendor actions and preparing for scalable production use.

You will collaborate with global hardware teams, vendor engineering, and cross-AWS accelerator initiatives, presenting findings to VP-level leadership

Qualifications

• Bachelor's degree in electrical engineering, computer engineering, or equivalent.
• 7+ years of hardware design and development experience for server, compute, or large-scale infrastructure platforms.
• Experience in developing functional specifications, design verification plans and functional test procedures.

Responsibilities

• Own vendor relationships across GPU platforms, coordinating roadmaps and escalations.
• Qualify new GPU SKUs and baseboard assemblies; define tests and gates.
• Define firmware qualification criteria and rollout policies.
• Drive RMA strategy: build failure evidence packages, negotiate acceptance criteria with vendors, manage submission quotas and pipeline velocity.
• Lead root-cause analysis on fleet-wide GPU failure modes using telemetry, event logs, and vendor diagnostics.
• Set GPU health standards: define metrics, thresholds and alerting for platform teams.
• Define GPU fleet health dashboards: telemetry, failure rate trends, and qualification status.

Skills

Data analysis at fleet scale

Vendor engagement

Education

Bachelor's degree in electrical engineering, computer engineering, or equivalent

Job description

Amazon in Cupertino is seeking a Senior Hardware Development Engineer to own the GPU lifecycle, from hardware and firmware requirements through qualification, field operations, and fleet-scale deployment. You will be the single-threaded owner of GPU lifecycle, translating fleet data into vendor actions and preparing for scalable production use.

You will collaborate with global hardware teams, vendor engineering, and cross-AWS accelerator initiatives, presenting findings to VP-level leadership