Overview
Architect a greenfield implementation of LLM-enabled technologies to support agentic workflows Deploy, operate, and monitor open-weight LLMs hosted on local Kubernetes clusters Design, build, and maintain RAG pipelines to enable use of document investigation, chunking, embedding, retrieval, and reranking with existing models and services Develop and maintain Model Context Protocol (MCP) servers and their interconnections to existing servicesCoach teams on best practice MCP designs and usage Support software automated testing environments