System Software Engineer
Core
Develop low-level diagnostic and stress software for next-generation data center GPUs and rack-scale AI systems to validate complex hardware components.
Role type
Senior IC system software engineer (hardware validation/diagnostics)
Builds
Diagnostic software, stress tests, and validation workloads for GPU hardware and AI systems
Domain
Data center AI computing, GPU architecture, embedded systems
Deliverable
production ML models | product features | infrastructure
Required skills
C/C++ programming, Python, embedded software development, Linux device drivers, hardware validation, silicon bring-up, computer architecture (memory, caches, DMA, buses), debugging complex hardware/software failures
Preferred skills
GPU architecture knowledge, CUDA programming, GEMM-style compute, NCCL, PyTorch-based workloads
Technologies
C, C++, Python, CUDA, NCCL, PyTorch, Linux, PCIe, NVLink
Responsibilities
Develop diagnostic and stress software in C/C++ and Python for complex hardware systems; Collaborate with hardware architects, driver developers, and manufacturing teams to bring up new hardware; Create targeted tests for compute engines, memory subsystems, and high-speed interfaces; Investigate hardware and software failures involving memory errors, ECC, and performance issues; Use modern development and analysis tools to accelerate coding and failure analysis
Seniority
Senior, hands-on IC