GPU Inference Performance Engineer — Equity & Optimization

Nvidia Corporation; Santa Clara (CA); On-site; USD 152,000 - 242,000; Full time

Job summary

NVIDIA is seeking a Senior Inference Performance Engineer to push the performance limits of large-scale AI inference benchmarks. You will optimize autonomous frameworks used by AI agents to run benchmarks, profile, and tune processes, aiming to maximize throughput per GPU while maintaining model correctness.

You will collaborate with TensorRT-LLM, vLLM, and other teams to translate profiling insights into delivered performance improvements, using Nsight systems and CUDA-based tools to drive

Qualifications

• BS/MS/PhD in CS/CE/EE/Applied Math or related field, or equivalent experience.

Responsibilities

• Distill performance instincts into reusable workflows for autonomous AI agents.

Skills

Python

C++/CUDA

Experimental methodology

Communication

GPU architectures

Education

BS/MS/PhD in CS/CE/EE/Applied Math or related

Tools

Nsight Systems

Nsight Compute

CUPTI

PyTorch profiler

Job description

NVIDIA is seeking a Senior Inference Performance Engineer to push the performance limits of large-scale AI inference benchmarks. You will optimize autonomous frameworks used by AI agents to run benchmarks, profile, and tune processes, aiming to maximize throughput per GPU while maintaining model correctness.

You will collaborate with TensorRT-LLM, vLLM, and other teams to translate profiling insights into delivered performance improvements, using Nsight systems and CUDA-based tools to drive