Sr. Data Center GPU Validation and Debug Engineer
Core
Validate and debug data center GPU products across the complete software and hardware stack, focusing on workload behavior, performance qualification, and root-cause isolation.
Role type
Senior IC GPU validation and debug engineer
Builds
Data center GPU platforms, firmware, and software releases for AI, HPC, and communication workloads
Domain
Semiconductor / High-Performance Computing
Deliverable
production ML models
Required skills
Linux systems engineering, C/C++, Python, shell automation, GPU architecture, memory hierarchy, parallel execution, log analysis, hardware telemetry, performance counters
Preferred skills
Linux kernel drivers, PCIe, firmware interaction, ROCm/HIP, RCCL, CUDA, PyTorch, vLLM, SGLang, roofline analysis, multi-GPU topology, NUMA, RAS, CI systems
Technologies
Linux, C, C++, Python, ROCm, HIP, CUDA, PyTorch, vLLM, SGLang, PCIe, NUMA
Responsibilities
Debug GPU failures including hangs, crashes, memory faults, and performance regressions; Reproduce failures and reduce them to minimal test cases; Triage system-level interactions across GPU, CPU, memory, networking, and power; Validate AI, HPC, and communication workloads; Characterize performance and identify bottlenecks; Build automated diagnostics and stress tests; Support customer-representative validation and escalation reproduction
Seniority
Senior, hands-on IC
