Senior Systems Software Engineer - Local AI on GPUs

Nvidia Corporation; Santa Clara (CA); On-site; USD 152,000 - 241,500; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA in Santa Clara, CA seeks a Senior Systems Software Engineer to tackle client-side AI challenges on Windows and Linux PCs with limited resources, partnering with software, research, architecture, and product teams to enable AI on RTX and DGX platforms.

You will optimize AI inference pipelines, work on low-level GPU programming with CUDA, and collaborate with industry partners to drive AI across graphics, edge devices, and open/closed source tech.

Qualifications

• Must have MS/BS/PhD in computer science or related field (or equivalent).
• Strong C++ programming and debugging skills with data structures and algorithms.
• 5+ years of experience with AI inference pipelines using ML/DL frameworks (ONNX RT, PyTorch, TensorRT, llama.cpp, vLLM).
• Excellent written and verbal communication; able to collaborate across teams.

Responsibilities

• Collaborate with software, research, architecture, and product teams to enable AI on RTX/DGX PCs.
• Optimize performance of AI models and inference runtimes; improve pipelines.
• Implement compute/memory optimizations (quantization, distillation, pruning) for large models.
• Contribute to both open and closed source technologies; support system-level integration.

Skills

Excellent C++ programming

AI inference pipelines

Strong analytical skills

Excellent communication

CUDA knowledge

DirectX/Vulkan

Education

Bachelor's/Master's/PhD in CS or related

Tools

ONNX RT

PyTorch

TensorRT

llama.cpp

vLLM

CUDA

DirectX

Vulkan

Job description

NVIDIA in Santa Clara, CA seeks a Senior Systems Software Engineer to tackle client-side AI challenges on Windows and Linux PCs with limited resources, partnering with software, research, architecture, and product teams to enable AI on RTX and DGX platforms.

You will optimize AI inference pipelines, work on low-level GPU programming with CUDA, and collaborate with industry partners to drive AI across graphics, edge devices, and open/closed source tech.