AI Infrastructure & Linux Systems Engineer
We're partnering with a client seeking an experienced AI Infrastructure & Linux Systems Engineer to deploy, secure, and support on-premises and customer-hosted AI environments. This role is ideal for someone with a strong Linux infrastructure background who has hands-on experience with NVIDIA GPU environments, private AI deployments, and open-source LLM platforms. Location: Hybrid (Minnesota/Wisconsin Preferred). Preference will be given to candidates located in Minnesota or Wisconsin who can work in a hybrid environment, though exceptional remote candidates are also encouraged to apply. Requirements:
- 5-10+ years of Ubuntu/Linux administration experience
- Strong experience with Linux security, OS hardening, SSH configuration, Bash scripting, and Docker
- Hands-on experience deploying and supporting NVIDIA GPU infrastructure, AI inference platforms, and local LLM deployments
- Experience implementing and managing AI/LLM platforms such as Ollama, vLLM, SGLang, Open WebUI, and embedding models
- Experience with Tailscale networking and secure remote access solutions
- Proven ability to troubleshoot complex system, networking, hardware, and AI platform issues
- Strong communication skills with the ability to lead customer-facing technical discussions, workshops, and implementation sessions
Preferred:
- Experience designing and deploying private AI environments
- Knowledge of RAG architectures, vector databases, model serving, and inference platforms
- GPU sizing, performance tuning, and AI infrastructure capacity planning experience
- Consulting or professional services background
The ideal candidate comes from a systems and infrastructure engineering background rather than a pure software development background and is comfortable working directly with customers while implementing and supporting modern AI environments.