> Markdown version of [/jobs/ext/4716328-senior-ai-platform-engineer](https://www.wearedevelopers.com/jobs/ext/4716328-senior-ai-platform-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Senior AI Platform Engineer - **Company:** University of the Cumberlands - **Location:** United States (Remote available) - **Experience:** Expert - **Contract:** Permanent contract - **Skills:** Application Programming Interfaces (APIs), Artificial Intelligence, Computing Platforms, Systems Engineering, User Authentication, Bash Shell, Nvidia CUDA, Continuous Integration, Linux, DevOps, General-Purpose Computing on Graphics Processing Units, Python (Programming Language), Language Modeling, Performance Tuning, AI Infrastructure, Generative AI, HybridCloud, AI Platforms, Kubernetes, Infrastructure Automation Frameworks, HuggingFace, Performance Monitor, Ollama, Machine Learning Operations, Nim (Programming Language), Api Gateway, VLLM, Docker - **Published:** November 14, 2026 - **Apply:** https://www.indeed.com/viewjob?jk=ea37e37c29f34885 ## About the Role * Significant professional experience in platform engineering, DevOps, systems engineering, or enterprise infrastructure, including demonstrated responsibility for deploying and supporting production AI/ML environments. * Hands-on experience deploying or administering NVIDIA GPU-based AI infrastructure, NVIDIA AI Enterprise, NVIDIA NIM, or comparable AI/ML and enterprise inference platforms. * Strong Linux, networking, containers, and modern infrastructure knowledge. * Scripting and automation experience with Python, Bash, or similar tools. * Familiarity with APIs, authentication, security, and monitoring; strong troubleshooting and collaboration skills. * Bachelor's degree in a related technical field or equivalent professional experience. Even Better If You Have * Direct experience with NVIDIA AI Enterprise and NVIDIA NIM; CUDA or GPU performance optimization. * Experience with vLLM, Ollama, Hugging Face, Docker, Kubernetes, infrastructure as code, or CI/CD. * Knowledge of MLOps/LLMOps, vector databases, embeddings, or retrieval-augmented generation (RAG). * Experience with enterprise API gateways, hybrid cloud, higher education, or research computing., We're looking for an experienced engineer who brings deep technical expertise, strong problem-solving skills, and a proven ability to design, deploy, and manage enterprise AI infrastructure. The ideal candidate has hands-on experience with GPU-accelerated computing, locally hosted large language models, and production AI platforms, along with the technical judgment to lead complex implementations from the ground up. If you're ready to bring your expertise to an exciting new initiative and help establish the foundation for enterprise AI at the University of the Cumberlands, we'd love to hear from you. ## Description * Bring models to life. Deploy, optimize, and maintain locally hosted LLMs and inference services using NVIDIA NIM, vLLM, Ollama, or comparable tools. * Make AI accessible. Build secure APIs and services connecting approved AI capabilities to University applications and users. * Keep things running. Monitor performance, optimize GPU resources, troubleshoot issues, and maintain security, reliability, and scalability. * Automate and improve. Use Linux, containers, scripting, and platform engineering practices to streamline operations. * Collaborate and shape what's next. Partner across IT and the AI Lab, evaluate emerging technologies, and influence platform architecture., * Build from the beginning. Help establish a new AI platform and shape its long-term direction. * Work with powerful technology. Get hands-on with NVIDIA GPU computing, enterprise AI software, and open-weight language models. * Make an impact. Support teaching, learning, research, and institutional innovation. * Have a voice. Help choose tools, set technical standards, and improve the platform as it grows.