Senior Platform Software Engineer, AI Server - GPU

Senior Platform Software Engineer, AI Server - GPU Job Location : 3535 Monroe St. Santa Clara, California 95051 United States NVIDIA’s invention of the GPU in 1999 sparked the growth of the PC gaming market, redefined modern computer graphics, and revolutionized parallel computing. More recently, GPU deep learning ignited modern deep learning — the next era of computing — with the GPU acting as the brain of computers, robots, and self-driving cars that can perceive and understand the world. Today, we are increasingly known as “the AI computing company.” We're looking to grow our company and establish teams with the most thoughtful people in the world. NVIDIA GH200 superchip provides performance and productivity required for strong scaling for HPC and generative AI workload. Scale out is inherent to design of this massive superchip. We are looking for expert engineers to come and help design rack level solutions for next generation scaling AI supercomputing platforms. We are looking for a strong technical platform software engineer focused on PCIe firmware. You will own the PCIe stack for all NVIDIA GPU servers from firmware and software perspective. You will work with various leads internally and externally, drive customer use cases, align architecture with customer requirements and release the best products to market. Join us at the forefront of technological advancement. What you’ll be doing: Drive and deliver innovations for GPU based AI server with focus on PCIe architecture, system engineering, software/firmware changes as per processor & I/O architecture. Define system architecture to optimize I/O performance for various GPU applications. Debugging complex system issues due to GPU, I/O bus (PCIe, etc.) and CPU. Architecting complex systems, I/O error handling from PCIe & other I/O buses and processor viewpoint, fault management for degraded mode operation of the system per datacenter requirements and improve resiliency of GPU based systems. Identify gaps in platform debuggability and drive solutions to improve speed and correctness of issue closure. Identify new technologies and features to improve performance, functionality, and uptime of GPU systems. Work across the industry to choose and enable new and required technologies and bring those to AI servers in the most efficient way. Contribute to all phases of product development, from product definition and architecture and design, through implementation, debugging, testing and early customer support. What we need to see: Deep understanding of Server Architecture, CPU design, PCI Express, and CXL at platform level for enterprise systems. Deep understanding of PCI Express and associated Error Handling (RAS) and Performance. Deep understanding of Linux kernel. Familiar with PCIe Switches and Retimers and associated firmware or configuration files. Deep understanding of Memory architecture with a focus on Memory RAS. Solid experience of end-to-end delivery of high-end enterprise servers from definition to customer deployment. Experience modifying UEFI BIOS and Linux Kernel source. Experience writing scripts to assist or automate debug. Experience with C/C++ development and debugging skills in Linux operating environments. Excellent written and oral communication skills, good work ethics, high sense of teamwork, love to produce quality work and commitment to finish tasks every single day. You are a self-starter who loves to find creative solutions to exciting problems. Bachelor's Degree in Electrical Engineering or Computer Science, or equivalent experience. At least 7+ years of experience as an individual contributor. Ways to stand out from the crowd: Proven expertise in debugging complicated and time-critical issues in both development and production environments. Experience with both x86 and Arm architectures. NVIDIA is widely considered to be one of the technology world’s most desirable employers. We have some of the most forward-thinking and talented people on the planet working for us. If you're creative and autonomous, we want to hear from you!

#J-18808-Ljbffr