AI Workflows & Agentic UX consultant. Building local LLM infrastructure on Apple Silicon clusters.
Currently running distributed inference on M3 Ultra machines (512 GB + 256 GB × 3) with Inferencer Pro — pushing 570 GB+ models locally, GDPR-compliant, zero cloud dependency.
What I do:
- Local LLM deployment & multi-tier routing (MLX, Inferencer, Ollama)
- Agentic UX — systems where AI processes first, humans decide after
- n8n automation pipelines (audio → Whisper → Claude → Notion)
- Quantization benchmarking with real-world professional tasks
Stack: MLX · Inferencer Pro · Ollama · n8n · Docker · Cloudflare Tunnels · Tailscale
Previously: 15 years UI/UX, European Commission.
📍 Brussels, Belgium · themonoclebear.com

