Senior Linux Kernel Systems Software Engineer – CSP Engagements

NVIDIA is seeking a Senior Software Engineer to join our CSP Engagements team, focusing on system software for Datacenter products such as GB200.

This role combines deep technical expertise in embedded firmware, Linux kernel development, and middleware development, with customer-facing responsibilities to enable cloud service providers with next-generation computing platforms.

You will work at the intersection of hardware and software, driving technical solutions from concept through deployment.

What you’ll be doing:

• Design and develop software solutions for data center servers including Linux kernel modifications, device drivers, and system optimizations for GB200 and next-gen platforms.
• Lead hardware bring-up activities, BSP development, and hardware-software co-design for Cloud Service Provider deployments.
• Partner directly with CSPs to deliver technical solutions, co-develop & co-debug features and optimizations, and provide support during new product introductions.
• Collaborate with cross-functional teams in designing end-to-end solutions spanning firmware, OS, middleware, and applications with focus on AI/ML and HPC workloads.
• Perform advanced system debugging, root cause analysis, and performance optimization for large-scale data center environments.
• Collaborate with AE, FAE, and Solution Architect teams to deliver integrated customer solutions and technical documentation.

What we need to see:

• Deep expertise in data center server architectures, HPC systems, and hardware-software co-design.
• Expert knowledge of Linux kernel internals, device drivers, communication protocols (PCIe, USB, Ethernet).
• Deep understanding of computer architecture, microprocessor concepts, and expert knowledge of ARM (aarch64) and x86 architectures.
• Ability to debug kernel crash dumps and all types of lock-up issues. Hands-on experience with GDB, kdump, and eBPF tracing to debug multiprocessor systems. Good understanding of ARM and Intel assembly.
• Strong understanding of PCIe virtualization and IOMMU.
• Deep understanding of NUMA architectures including memory topology, processor-memory locality, and performance optimization for multi-CPU systems in data center environments.
• Strong programming skills in C/C++, Python, plus experience with virtualization, Kubernetes, and cloud-native architectures.
• Skilled in complex system-level debugging, performance analysis, and test design.