Edge Agentic AI Developer Tech Engineer

NVIDIA; Santa Clara (CA); On-site; USD 152,000 - 287,500; Full time

Job summary

NVIDIA is seeking a Developer Technology Engineer in California to advance agentic AI workflows on RTX and DGX platforms. You will collaborate across internal teams and with external developers to deploy and optimize end-to-end AI pipelines.

You will lead profiling and debugging efforts, develop training materials and sample code, and contribute to OSS projects to improve runtime performance and user experience. Collaboration and mentorship are essential.

Qualifications

• 5+ years of professional experience in local GPU deployment, profiling and optimization.
• Bachelor's or Master's degree in Computer Science, Engineering, or a related field.
• Strong proficiency in C/C++ and Python, with software design skills.
• Experience with Windows and Linux development; CUDA and Nsight tooling.

Responsibilities

• Collaborate with internal and external teams to deploy GPU-based agentic AI workflows on NVIDIA RTX & DGX.
• Profile and optimize end-to-end AI workflows to maximize runtime efficiency.
• Prepare trainings, sample code, and host presentations on deployment best practices.
• Contribute to OSS projects like GGML, Llama.cpp, Ollama, and ONNX Runtime to improve user experience.
• Provide technical leadership and mentorship within the team.

Skills

C/C++

Python

CUDA

Nsight

Windows

Linux

Education

Bachelor's or Master's in CS/Engineering

Tools

Nsight GPU profiling

CUDA Toolkit

Job description

NVIDIA is seeking a Developer Technology Engineer in California to advance agentic AI workflows on RTX and DGX platforms. You will collaborate across internal teams and with external developers to deploy and optimize end-to-end AI pipelines.

You will lead profiling and debugging efforts, develop training materials and sample code, and contribute to OSS projects to improve runtime performance and user experience. Collaboration and mentorship are essential.