Senior GPU Networking Architect: AI-Scale Kernel Design

NVIDIA Corporation; Zürich; On-site; CHF 180,000 - 260,000; Full time

Job summary

NVIDIA is seeking a Senior GPU Networking Architect in Switzerland to join our networking software team, focusing on GPU-driven communication for large-scale AI systems. You will design, optimize, and implement GPU communication kernels that bridge GPU computation with high-performance networks.

This role requires deep CUDA expertise, strong C/C++ systems programming, and experience with GPU data movement and profiling tools.

Qualifications

• 5+ years of hands-on CUDA programming and GPU kernel optimization.
• M.Sc. or equivalent degree in CS/CE or related field.
• Strong understanding of GPU architecture, including warp scheduling and memory hierarchy.
• Experience with systems-level C/C++ development in performance-critical environments.
• Familiarity with GPU data movement mechanisms (GPUDirect RDMA, GPU-initiated communication).
• Ability to read and act on GPU performance profiles (Nsight Compute/Systems).
• Strong collaboration skills in a multi-national, interdisciplinary environment.

Responsibilities

• Build, implement, and optimize GPU communication kernels for large-scale AI systems.
• Leverage knowledge of GPU architecture to improve kernel efficiency and reduce latency.
• Develop GPU-resident communication primitives and device-side APIs for cross-node data movement.
• Profile and tune GPU kernels end-to-end, identifying bottlenecks at compute/memory/network junctions.
• Collaborate with network hardware, software, and AI framework teams to align with GPU execution.

Skills

CUDA programming

GPU kernels

GPUDirect RDMA

C/C++ development

Nsight tools

GPU architecture

Education

M.Sc. or equivalent degree

Tools

NCCL/NVSHMEM

PyTorch/TensorRT-LLM

Job description

NVIDIA is seeking a Senior GPU Networking Architect in Switzerland to join our networking software team, focusing on GPU-driven communication for large-scale AI systems. You will design, optimize, and implement GPU communication kernels that bridge GPU computation with high-performance networks.

This role requires deep CUDA expertise, strong C/C++ systems programming, and experience with GPU data movement and profiling tools.