Systems Design Engineer - dGPU / CPU Software Feature Enablement
Overview:
As ROCm Feature Enablement Technical Lead, you will steer pre-silicon planning, post-silicon bring-up, and system validation for Client and dGPU programs. You'll translate product and customer requirements into actionable feature plans and validation criteria, ensuring on-time execution. You lead cross-functional discussions, triage issues, and drive improvements in validation efficiency through automation. This role sits in a team that advances high-quality GPU technologies and enables AMD to deliver industry-leading products. You'll collaborate across architecture, firmware, software, and validation to shape feature readiness and program milestones.
Responsibilities:
- Lead ROCm feature enablement for Client and dGPU programs
- Plan pre-silicon and post-silicon validation and ensure on-time execution
- Define feature lists, validation plans, test strategies, dependencies, coverage, and exit criteria
- Collaborate with architecture, design, firmware, software, diagnostics, and validation teams to drive readiness
- Lead triage, root-cause analysis, debugging, and verification during bring-up, validation, and production phases
- Drive validation efficiency via automation, tooling, scripting, and process improvements
- Champion technical innovation and contribute to cross-functional initiatives to strengthen validation capabilities
Key requirements:
- Strong knowledge of GPU architecture, system software, validation, and debugging
- Strong communication, technical leadership, and cross-functional collaboration skills
- Hands-on experience with ROCm, Linux GPU drivers, HIP, AI or compute workloads, and GPU software stacks
- Strong hardware and software debugging skills
- Experience developing test plans, test cases, scripts, and automation
- Experience utilizing AI agents and automation technologies to improve productivity and operational efficiencycommunicationleadershipcross-functional collaborationROCmLinux GPU driversHIP