Responsible AI Engineer (On-Prem LLMs)

Texas Integrated Services builds on-prem AI servers for small Texas businesses so they can run LLaMA, Mistral, and similar models on hardware they own. You'll deploy, tune, and support those systems end-to-end. You'll work across model quantization, vector databases (Qdrant), RAG pipelines, and hands-on server hardware setup. The mission is clear: keep customer data out of third-party APIs and in the customer's own infrastructure. Ideal candidate: comfortable in both the GPU stack and in a client's server closet, and principled about what data should and should not leave a customer's building.