Open to AI Engineer roles · EU / UK / remote

Nico Mastakas

AI Engineer building LLM agents, RAG and evals in production.

Product engineer, not a feature engineer, now with AI in the stack. My edge isn't calling the model; it's building and operating the whole system around it: agents, retrieval, evals, and the token economics to run it in production. Six-plus years shipping solo, end to end.

LLM agents & RAG
Agentic systems with bounded tool-use loops, memory and MCP; grounded, cited retrieval. LangChain / LangGraph, or hand-rolled when it earns it.
Evals & fine-tuning
LLM-as-judge calibrated against humans (κ 0.81); QLoRA fine-tuning measured on a labelled set. The model is an instrument, not magic.
The token economy
FinOps for LLMs: right model per task, caching, context budgets, hard cost caps. Production, not a demo bill.

Selected work

07 projects

More work

More on GitHub