On-Prem AI Engineer: LLaMA/Mistral, GPUs & RAG

Texas Integrated Services seeks experts to deploy and maintain on-prem AI infrastructure for healthcare-adjacent clients. You will work across GPU deployment, model quantization, vector databases like Qdrant, and RAG pipelines, while safeguarding data and staying within client networks. The role requires hands-on server hardware setup and a thoughtful approach to data leaving the building. Travel within Texas for install days is required; familiarity with HIPAA and client privacy is important to

#J-18808-Ljbffr