Senior GPU Systems Performance Architect

NVIDIA Corporation; United States; On-site; USD 150,000 - 190,000; Full time

Job summary

NVIDIA Corporation in the United States is seeking a Senior Validation Engineer to join the DGX Server Product Engineering Team. You will collaborate with HW/SW engineers to develop and implement automated test plans for our GPU-accelerated computing products.

You will design synthetic GPU workloads with CUDA, onboard AI training and inference workloads to new platforms, build system-level performance models, run controlled experiments, analyze anomalies, and automate workload deployment and

Qualifications

• BS in Computer Engineering, Electrical Engineering, CS, or related field.
• 5+ years in systems performance engineering or related fields.
• Deep understanding of computer architecture (GPU/CPU, memory hierarchies).
• Experience developing analytical or simulation-based performance models.
• Hands-on experience deploying and tuning AI workloads with PyTorch, TensorRT-LLM, vLLM, or SGLang.
• Strong Python programming and data analysis skills.
• Knowledge of CUDA and GPU profiling tools.
• Experience debugging workloads in Linux and collaborating across teams.

Responsibilities

• Develop and tune synthetic GPU workloads using CUDA and AI workloads to stress hardware subsystems.
• Onboard and adapt AI training and inference workloads to new GPU platforms.
• Build system-level performance models to characterize workload behavior and bottlenecks.
• Design controlled experiments and compare model predictions with telemetry and results.
• Analyze performance anomalies and collaborate to drive fixes and verify improvements.
• Build automation for workload deployment, experiment execution, telemetry collection, and analysis.

Skills

Systems performance engineering

Performance modeling

Accelerated computing

Complex system development

Debugging

Python programming

CUDA programming

GPU profiling

Linux debugging

Data analysis

Education

BS in Computer Engineering, Electrical Engineering, Computer Science or related field

Job description

NVIDIA Corporation in the United States is seeking a Senior Validation Engineer to join the DGX Server Product Engineering Team. You will collaborate with HW/SW engineers to develop and implement automated test plans for our GPU-accelerated computing products.

You will design synthetic GPU workloads with CUDA, onboard AI training and inference workloads to new platforms, build system-level performance models, run controlled experiments, analyze anomalies, and automate workload deployment and