Senior AI Deployment & Performance Engineer

NVIDIA Corporation; United States; On-site; USD 152,000 - 288,000; Full time

Job summary

NVIDIA Corporation in the United States seeks a seasoned GPU deployment engineer to drive end-to-end AI workflows, profiling, and optimization across demanding workloads. You will collaborate with internal teams and external developers to enhance runtime efficiency and user experience.

The role requires 5+ years of GPU deployment, strong C/C++, Python, CUDA experience, and the ability to travel for conferences and partner visits. Join a world-class team advancing AI and accelerated computing.

Qualifications

• 5+ years of professional experience in local GPU deployment, profiling or optimization.
• Bachelor's or Master’s degree in Computer Science, Engineering, or related field.
• Strong proficiency in C/C++, Python, and software design/techniques.
• Familiarity with Windows and Linux, CUDA, and Nsight tooling.
• Some travel for conferences and on-site partner visits.

Responsibilities

• Collaborate with internal engineering and product teams to deploy end-to-end GPU workflows.
• Profile and debug to improve runtime performance and resource utilization.
• Provide hands-on guidance, sample code, and trainings on GPU deployment.
• Contribute to OSS projects (e.g., GGML, Llama.cpp, Ollama, vLLM, ONNX Runtime).
• Mentor junior engineers and influence next-gen GPU features with feedback from real-world workflows.

Skills

C/C++

Python

Software design

Programming techniques

Education

Bachelor's or Master's in CS/Engineering

Tools

CUDA

Nsight

Job description

NVIDIA Corporation in the United States seeks a seasoned GPU deployment engineer to drive end-to-end AI workflows, profiling, and optimization across demanding workloads. You will collaborate with internal teams and external developers to enhance runtime efficiency and user experience.

The role requires 5+ years of GPU deployment, strong C/C++, Python, CUDA experience, and the ability to travel for conferences and partner visits. Join a world-class team advancing AI and accelerated computing.