# Lorenzo Germini

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

## 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.

## Professional profile

- [Homepage](https://lorenzogermini.com): Professional hub, positioning, and the writing
- [Homepage as markdown](https://lorenzogermini.com/index.md): The same hub as markdown, generated from the profile data
- [Writing](https://lorenzogermini.com/writing): Essay index, built from the germinai feed; every essay links out to Substack
- [Writing as markdown](https://lorenzogermini.com/writing.md): The same frame as markdown, generated from the profile data
- [germinai](https://lorenzogermini.substack.com): Field notes, mostly on building with AI
- [CV](https://lorenzogermini.com/cv): Canonical curriculum vitae with full experience, education, skills, and contact details
- [CV as markdown](https://lorenzogermini.com/cv.md): The same CV as markdown, generated from the profile data
- [CV PDF](https://lorenzogermini.com/lorenzo-germini-cv.pdf): Downloadable build-synchronized curriculum vitae
- [Full profile](https://lorenzogermini.com/llms-full.txt): Long-form machine-readable profile with every role, project, and contact detail

## 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

## Links

- [GitHub](https://github.com/Blaise-g): Projects and open-source code
- [LinkedIn](https://www.linkedin.com/in/lorenzogermini/): Professional profile
- [X/Twitter](https://twitter.com/spleenboi_): Updates and thoughts

## Skills

LLM agents, RAG, Evals & tracing, Full-stack development, Python

## Experience

- AI Engineer at Complaion (May 2025 - Present): 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.
- Founding AI Engineer at Stealth GenAI Startup (Nov 2024 - Apr 2025)
- AI Engineer at GSK (Sep 2023 - Oct 2024)
- Teacher and Digital Freelancer (Nov 2022 - Aug 2023)
- Engineering Intern at Burgeon Labs (Feb 2022 - Oct 2022)
- Summer Intern at Roche - Think Tank in Innovation & Sustainability (Jul 2021 - Oct 2021)

## Education

- MSc in Life Sciences Engineering (Neuroscience & Neuroengineering), Swiss Federal Institute of Technology Lausanne (EPFL) (2020-2022)
- Bachelor's Degree in Electrical Engineering, Polytechnic of Turin (2017-2020)

## Projects

- L'Oracolo della Ghigliottina: AI game companion for the final round of Italy's most-watched quiz show. 100% accuracy so far, with rate-limit handling
- Biomedical Paper Summarizer: MSc thesis work, an end-to-end pipeline turning full-text biomedical papers into a detailed analysis or a TL;DR