Edge Agentic AI Engineer - GPU Deployment & Profiling

NVIDIA Corporation; Santa Clara (CA); On-site; USD 152,000 - 288,000; Full time

Benefits offered by this job

Equity

Benefits

Competitive salary

Job summary

NVIDIA Corporation in Santa Clara, CA is seeking a Developer Technology Engineer to drive end-to-end agentic AI deployment with RTX & DGX platforms. You will collaborate across internal teams and with external developers to advance GPU-powered AI workflows.

The role requires 5+ years in local GPU deployment, expertise in C/C++, Python, CUDA and Nsight, and willingness to travel for conferences and partner visits.

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++, Python, and software design.
• Experience with Windows and Linux development environments.
• Hands-on experience with CUDA and NVIDIA Nsight tools.
• Willingness to travel for conferences and on-site partner visits.
• Strong problem-solving and collaborative skills.

Responsibilities

• Collaborate with internal and external teams to deploy end-to-end agentic AI on NVIDIA RTX & DGX.
• Apply profiling and debugging tools to optimize runtime performance.
• Conduct hands-on trainings, develop sample code, and present guidance for efficient AI deployment.
• Improve LLM/GenAI UX by contributing to OSS projects (e.g., GGML, Llama.cpp, Ollama, vLLM, ONNX Runtime).
• Collaborate with GPU driver/architecture teams and NVIDIA research to influence next-gen GPU features.
• Provide technical leadership and mentorship to junior engineers.

Education

Bachelor's degree or Master's degree in Computer Science, Engineering, or related field

Tools

GGML

Llama.cpp

Ollama

vLLM

ONNX Runtime

Job description

NVIDIA Corporation in Santa Clara, CA is seeking a Developer Technology Engineer to drive end-to-end agentic AI deployment with RTX & DGX platforms. You will collaborate across internal teams and with external developers to advance GPU-powered AI workflows.

The role requires 5+ years in local GPU deployment, expertise in C/C++, Python, CUDA and Nsight, and willingness to travel for conferences and partner visits.