AI Engineer

I build systems that reason, retrieve, and ship to production.

Mirco Gnuva — I build LLM-powered agents and tools in Python: from autonomous browser agents to self-evaluating RAG pipelines.

mirco@gnuva: ~ — zsh
$ whoami
ai_engineer @ Elmec Informatica
$ cat focus.json
"retrieval", "evaluation",
"inference", "llms"
$ status --open

#Selected work

06 / projects
01

Portfolio — personal site

Single-page Astro static site with a dual light/dark 'blend' design and an animated canvas background. No UI framework; deployed on Cloudflare Pages with automatic builds on push.

AstroCloudflare PagesTypeScriptcanvas
this site
02

AIGuessr — autonomous geolocation agent

Vision LLM agent that plays OpenGuessr autonomously: drives a real browser via Playwright, reasons over panorama screenshots, and runs a two-stage exploration → guessing loop with Langfuse tracing.

pydantic-aiPlaywrightvisionLangfuse
vision agent
03

UniHelper — AI study-notes generator

Multimodal pipeline that ingests PDFs, scanned documents, images, tables, and audio (via faster-whisper), then generates study notes with an LLM and auto-evaluates them through a self-correcting regeneration loop.

PythonRAGevalsGradio
self-evaluating
04

MealsPlanner — conversational meal planner

Multi-agent meal-planning assistant (master + plan-generator agents) with a multilingual Chainlit UI, eval-golds dataset for quality measurement, and full Docker Compose deployment.

pydantic-aiOpenAIChainlitDocker
multi-agent
05

Packly — packing assistant with memory

Conversational packing assistant powered by a pydantic-ai agent with persistent mem0 memory, a Chainlit UI, FastAPI backend, SSE streaming, and Langfuse observability.

pydantic-aimem0ChainlitFastAPI
persistent memory
06

MoviePick — group movie-night picker

Shared movie backlog and multi-person voting app: each member rates candidates, the app surfaces the consensus pick. Streamlit UI, FastAPI backend, MongoDB storage.

StreamlitFastAPIMongoDBPython
group voting

#About

// who

I'm an AI Engineer who thinks in full cycles — from architectural design and stakeholder alignment to implementation, evaluation, and long-term performance monitoring. Shipping a feature is the beginning, not the end.

At Elmec Informatica I build LLM agents, RAG pipelines, and evaluation infrastructure. The decisions I care most about are the ones that determine whether a model-powered feature is durable: the eval harness, the feedback loops, the observability layer that tells you when something quietly degrades.

Outside work I run personal experiments and follow research to stay ahead of what's possible. I'm methodical enough to want systems that are measurable and honest about their failure modes — and curious enough to explore ideas before they're proven.

role AI Engineer
based North Italy
focus python · data · ai
exp_yrs 4

#Stack

// proficiency.map
Pythoncore
pydantic-ai / LLM agentscore
RAG & evaluationcore
FastAPIfluent
Chainlit / Gradio / Streamlitfluent
Data (pandas · MongoDB)fluent

#Path

// experience
Aug 2023 — present

AI Engineer

Elmec Informatica

Lead the retrieval and evaluation platform powering the core product. Set the bar for how models are tested before they reach users.

Sep 2022 — Aug 2023

Technology Architect

Elmec Informatica

Developed software solutions integrating different tools to create new products and services.

Sep 2022 — present

M.Sc. Computer Science

Università degli Studi di Milano

Laurea Magistrale in Scienze e Tecnologie Informatiche.

2016 — 2021

B.Sc. Informatics

Università degli Studi di Milano

Laurea triennale in Informatica. Graduated 100/110.

2011 — 2016

Diploma, Elettronica

IIS Marconi Galletti

Elettronica e Elettrotecnica. Graduated with top marks.