AI Infrastructure Engineer, Local LLMs, RAG, AI Agents, Vector DBs
États-Unis
Anglais
Certaines informations sont présentées en anglais.
À propos de moi
I build private AI systems that run on YOUR hardware. No cloud, no data leaving the building. My own lab runs dual-GPU NVIDIA inference (RTX 5090) serving quantized models through vLLM, with a self-hosted RAG pipeline, vector store, and knowledge graph over terabytes of my own operational data. I use what I sell daily. Background: BS in Artificial Intelligence, US military veteran, solo founder of a 120+ app Android portfolio with live ad and IAP monetization. I deliver working systems, documented and reproducible, not slide decks. If it needs to run offline and never fail, that's my lane.... Plus d’infos