Senior GPU Systems Performance Engineer (On‑Site) + Equity

NVIDIA Corporation; Santa Clara (CA); On-site; USD 136,000 - 259,000; Full time

Job summary

NVIDIA is seeking a Senior Validation Engineer for the DGX Server Product Engineering Team in Santa Clara. You will work with HW/SW engineers to design and implement automated test plans for GPU-accelerated computing products.

Responsibilities include system architecture, performance modelling, and validating new models. The role requires hands-on lab work, deep knowledge of CUDA/CUBLAS/Cutlass, and Python-based testing across data center products.

Qualifications

• Bachelor’s degree in Electrical or Computer Engineering or equivalent.
• 5+ years validating and debugging complex systems in hardware/software environments.
• Experience with ML/LLM workloads and GPU acceleration is required.

Responsibilities

• System architecture, design and performance modelling for new models and packages.
• Enable GPU SKU bring up, validation and model enablement in a lab setting.
• Develop system-level stress tests and performance testing strategies using DL/AI apps.

Skills

5+ years experience

Dynamo

TensorRT

Slurm

BCM

Cuda

Cublas

Python

Education

Bachelor's degree in Electrical or Computer Engineering

Tools

Dynamo

TensorRT

Slurm

BCM

Cuda

Cublas

Cutlass

Python

Job description

NVIDIA is seeking a Senior Validation Engineer for the DGX Server Product Engineering Team in Santa Clara. You will work with HW/SW engineers to design and implement automated test plans for GPU-accelerated computing products.

Responsibilities include system architecture, performance modelling, and validating new models. The role requires hands-on lab work, deep knowledge of CUDA/CUBLAS/Cutlass, and Python-based testing across data center products.