JP Javier Pontón / AI Engineer CV

Grabia

Self-hosted meeting intelligence, fully local AI

Private inference node Self-hosted Founder and sole engineer

What it is

Local pipeline with WhisperX transcription and pyannote diarisation feeding a LangChain and LangGraph agent that produces structured summaries, decisions and action items, with RAG over the meeting archive. Served from a private node (Ryzen AI MAX+ 395, 128 GB, ROCm) running Qwen3-30B under Ollama and mistral.rs; nothing leaves the machine.

Stack

  • Python
  • LangChain
  • LangGraph
  • WhisperX
  • pyannote
  • Ollama
  • mistral.rs
  • ROCm
  • Qwen3