# Lorenzo Germini — AI Product Engineer

> AI Product Engineer shipping AI products end-to-end across compliance, health, and education. Based in Cuneo, Italy, CET.

## Profile

I'm an AI product engineer: I ship AI products end-to-end, from the models and infrastructure to the interface people actually touch, and stay on the hook for whether the thing helps anyone. Full stack in the literal sense: backend, frontend, and the product calls in between.

These days that's the AI engine behind Complaion, a compliance platform for European SMEs getting and keeping ISO certifications. The interesting problem is making the agents in the background reliable enough to trust with real compliance work, and knowing when they're not. Before that: AI for pharma manufacturing at GSK, AI R&D in digital health, and a GenAI EdTech startup I built as founding engineer. The through-line hasn't changed: technical depth only matters when it meets a real user problem.

Outside work: sports, side projects, and rabbit holes on tech entrepreneurship and biohacking.

## When to use this

Good fit for: putting LLM agents into production where being wrong is expensive — regulated documentation, compliance, health, pharma manufacturing; building the eval and tracing harness for an AI system that already ships but nobody trusts yet; taking a GenAI product from prototype to production as the engineer who owns the backend, the interface, and the product calls in between.

Less good fit for: research roles with no product surface, ML infrastructure work that ends at the model, or anything where shipping to real users is somebody else's problem.

Contact: lorenzo.germini@icloud.com

## What I do

I build AI products end-to-end and write about what actually works.

Right now that's the AI engine behind Complaion, a compliance platform for ISO certifications: LLM agents doing real compliance work in the background, and the evals that show when they can't be trusted. Before that: pharma manufacturing, digital health, and a GenAI startup.

## Writing

Field notes, mostly from building with AI, published on germinai. No definitive guides. Things I tried, what broke, and what earned its place.

### Drop the Bloat
Everything you hand a coding agent, it has to carry. Mine was hauling 35K tokens of instructions before I typed a word. A field note on cutting that to 13K, and on knowing when context stops earning its place.
Link: https://lorenzogermini.substack.com/p/drop-the-bloat

- Index: https://lorenzogermini.com/writing — as markdown: https://lorenzogermini.com/writing.md

## Work

### AI Engineer at Complaion (May 2025 - Present)
Location: Cuneo, Italy
Link: https://www.complaion.com/
- Complaion helps European SMEs implement, maintain, and get real value from ISO certifications.
- Building the AI engine behind it: agentic RAG over ISO documentation, and the evaluation frameworks that show when it can't be trusted in production.
- Shipping AI product features and automation workflows end-to-end, from prototype to production.

### Founding AI Engineer at Stealth GenAI Startup (Nov 2024 - Apr 2025)
Location: Cuneo, Italy
- Built the backend and GenAI API layer from zero on AWS (DynamoDB, Amplify, Lambda) for an EdTech product.
- RAG stack on pgai with custom parsing pipelines for machine-readable and handwritten content, plus tracing and evaluation workflows to tune prompts and retrieval quality.
- Led MVP engineering, managing two other developers.

### AI Engineer at GSK (Sep 2023 - Oct 2024)
Location: Saint-Amand-les-Eaux, France
Link: https://www.gsk.com/en-gb/home/
- Used Python and multi-source sensor data to find inefficiencies across pharmaceutical utilities; designed water rejection strategies projected to save 10,000 m³ annually.
- Anomaly detection and time-series forecasting for manufacturing operations, plus semantic NLP for fault detection and maintenance decisions.
- Natural-language interfaces and generative AI use cases that made plant data usable on the floor.

Earlier: A Stable Diffusion interior-design MVP, killed on the evidence; Biomedical-literature summarisation at Burgeon Labs; Fill-parameter ML at Roche; EPFL MSc, Life Sciences Engineering.

The complete record, with every role, project and grade: https://lorenzogermini.com/cv — as markdown: https://lorenzogermini.com/cv.md

## Projects

### L'Oracolo della Ghigliottina
Tags: Side Project, Live
AI game companion for La Ghigliottina, the cult final round of Italy's most-watched quiz show. Send the five clue words, typed or snapped from the TV, and it finds the one that connects them. 100% accuracy so far, with rate-limit handling because Italians take this game seriously.
Link: https://ghigliottina.vercel.app/

## Systems

agent systems · eval harnesses & tracing · end-to-end shipping, coding agents in the loop

## Contact

- Email: lorenzo.germini@icloud.com
- Website: https://lorenzogermini.com
- GitHub: https://github.com/Blaise-g
- LinkedIn: https://www.linkedin.com/in/lorenzogermini/
- X: https://twitter.com/spleenboi_