- Remote, United States
- Remote
- Full-time · Senior
Help design, deploy, and grow an on-premises environment powered by NVIDIA GPU infrastructure and NVIDIA AI Enterprise, supporting large language models (LLMs), high-performance inference, and secure APIs.
Responsibilities
- Design, deploy, and manage on-premises and hybrid AI infrastructure, including NVIDIA GPU environments and NVIDIA AI Enterprise
- Deploy, optimize, and maintain locally hosted LLMs and inference services using NVIDIA NIM, vLLM, Ollama, or comparable tools
- Build secure APIs and services connecting approved AI capabilities to University applications and users
- Monitor performance, optimize GPU resources, troubleshoot issues, and maintain security, reliability, and scalability
- Use Linux, containers, scripting, and platform engineering practices to streamline operations
Requirements
- Bachelor’s degree in a related technical field or equivalent professional experience
- Nice to have: CUDA
- Nice to have: GPU performance optimization
- Nice to have: vLLM
- Nice to have: Ollama