AI Engineer based in Valladolid, Spain · Remote-first
I design complex systems and build them by directing AI as my engineering team. LLM orchestration · GPU infrastructure · Observability · On-premise inference.
A multi-agent local AI ecosystem with episodic memory, cross-model validation and full LLM observability — running on a custom dual-GPU rig.
- 20+ years operating production infrastructure where downtime is measured in € / minute
- Self-taught in AI, LLMs and GPU systems since late 2024
- Validated by ModelVault (on-premise AI startup) — "great fit for our team"
Python · FastAPI · asyncio · PostgreSQL + pgvector · Redis · Ollama · Docker · CUDA · systemd
- llm-inference-docker-gpu — On-premise LLM inference with Docker, Ollama, GPU monitoring and structured telemetry.