Verification, Validation & Test
Lead the end-to-end diagnostics strategy and ROCm-based test coverage for the AMD Instinct Helios rack-scale platform.
About the role
As the Diagnostics Technical Lead, you will own the technical direction of the diagnostics solution for Data Center GPU (DCGPU) programs from pre-silicon emulation through high-volume manufacturing. A primary focus involves driving system-level test coverage for the AMD Instinct Helios rack-scale platform and compute trays using ROCm-based diagnostics.
What you'll do
- Own the end-to-end diagnostics solution, RTL coverage requirements, and system-level feature verification plans across software-based and FPGA-based emulation models.
- Lead diagnostics through SoC bring-up, feature enablement, performance profiling, and system-level debug of complex hardware and software issues to root cause.
- Define system-level test coverage for AMD Instinct series from single GPU and compute trays to the Helios rack-scale solution, including scale-up fabric (UALink over Ethernet) and scale-out networking (Ultra Ethernet with AMD AI NICs).
- Develop ROCm-based diagnostics and stress workloads for compute, HBM, and interconnect to validate tray and rack health at scale.
- Establish rack-level burn-in, health-check, fault-isolation flows, RMA isolation, and manufacturing test-time targets in partnership with Product Engineering and contract manufacturers.
What you'll need
- Bachelor's or Master's degree in Computer Science, Computer Engineering, Electrical Engineering, or a related field.
- Experience in software development, silicon validation, or diagnostics, including technical leadership experience.
- Hands-on experience with C/C++ programming for verifying complex IP blocks and system-level features.
- Experience with SoC bring-up, IP/SoC verification, and system-level debug across hardware and software.
- Proficiency with Linux and version control systems such as Git or Perforce.
Nice to have
- Experience with system-level test (SLT) and diagnostics across assembled GPU boards (L6), compute trays (L10), and full racks (L11).
- Working knowledge of GPU interconnects and data center networking, including PCIe, AMD Infinity Fabric, and Ethernet/RDMA.
- Experience developing GPU diagnostics or stress tests on ROCm or comparable GPU software stacks.
- Hands-on experience with pre-silicon emulation, FPGA prototyping platforms, or low-level firmware/device driver development.
- Knowledge of rack-scale infrastructure, including OCP Open Rack, liquid cooling, power shelves, BMC/Redfish, and out-of-band management.
- Experience applying machine learning or AI agents to test coverage, failure analysis, and automated root-cause analysis.
Skills: Diagnostics, SoC Bring-up, ROCm, GPU, System-Level Test
Market context
- First seen in our index: 20 Nov 2026 (our observation date)
- Last confirmed on the employer's career site: 20 Nov 2026
- Specialty: Post-Silicon Validation (Silicon Validation)
- Comparable active jobs: 522 at 73 employers, as of 20 Nov 2026
- Related specialties (Silicon Validation & Test family): 2598 active jobs at 136 employers
View all AMD jobs · Silicon validation jobs · Texas jobs
How we counted: postings read from employer career sites; dates are our observations unless labelled as the employer's. How we count