I do my best work on problems nobody has cracked yet, the kind where you invent the approach before you can follow it. I've put production ML on a Fortune-500 sales floor at Procter & Gamble, led the AI work at GF Machining Solutions, and built a CHF 500K+ coffee e-commerce from scratch. It's the one whose pricing, restocking, support and cost-checks I still keep running today, mostly on autopilot.
Before industry I did research at IDSIA and co-authored a published paper on optimisation under uncertainty. I hold an MSc in Artificial Intelligence from IDSIA. I'm based in Zürich and open to AI, ML and automation roles around Zurich, Zug and Basel, or remote.
Outside of work I've spent years volunteering. I'm a trained first responder with the Samaritans and a scout educator, and I organise local projects with the Global Shapers, the World Economic Forum's network for young leaders. I put technology and plain effort where they land on people who need them.
That instinct shows up in the work too: social-sport programs that give kids a free, safe place to move, and data-journalism tools that hold local newsrooms to account. Both come from the same place as the engineering.
A few highlights where ML or automation made a measurable difference. Every number is real and defensible.
A 3D, explorable map of what I've studied: hundreds of concept bubbles from my own Coursera transcripts, wired by typed links and grown by a local LLM whose every edit I can preview and undo. It grows most days, and I use it daily.
My main project: a system that merged our marketplace data with public sources and told each salesperson when and where to act, delivered entirely over email: briefings out, commands back in the replies. It found money in the noise the reps had no time to mine.
An ML tool that scored sales opportunities and suggested the margin to quote for the odds a rep wanted, tuned to the rep and the client. I validated it live against the sellers' own predictions, and it won executive backing for AI.
My father had the coffee idea, and the customers weren't coming. I moved the shop to Shopify, took over the marketing, and grew it past CHF 500K in its first year.
Local-first, it pulls Swiss job postings, scores each one against my own profile, and rolls the gaps into the two answers I care about: which skills to study next, and which roles are worth pursuing. A supervised browser extension handles the applications.
I met the head of quality while networking and told him I could turn six years of messy NPS comments into something useful, fast. Thousands of free-text answers, a dozen languages, shop-floor spelling. I built the pipeline that sorted them into praise and criticism, by theme and by country.
A through-line across my life: I show up, and I put the effort where it helps.
A trained first-aid volunteer, on call for public events and emergencies. When something goes wrong in a crowd, I'm one of the people who moves toward it.
Years spent guiding kids and teenagers in scouting. You take a group of restless kids and a weekend outdoors, and your job is to bring them home tired and a little braver.
Part of the Global Shapers, the World Economic Forum's civic network of young people. Most of what we take on is local, run by volunteers between day jobs.
I ran after-school sport programs that gave kids a free, safe place to move and belong. For some of them, showing up mattered more than the game.
Kept a community association running as its president: mostly organising volunteers and keeping them motivated when nobody's getting paid, which is harder than it sounds.
Volunteer time for TEDxLugano's events and for WWF, and a stretch at Impact Hub Ticino alongside people trying to start something of their own.
A generative-AI platform that turned real personal stories into illustrations, then into a printed, QR-linked exhibition. This is the one where the work and what I care about lined up completely.
I run the AI and data side of a live coffee e-commerce. Pricing and restocking now run themselves, and a cost-watch flags supplier overcharges. Support automation is next in line.
Led pro-bono technology and data projects for non-profits. I built free websites for local NGOs, among them the Samaritans and the Scouts, and created two AI projects: Racconti Invisibili, which turned real personal stories into a printed, QR-linked exhibition, and Oltre al titolo, an NLP analysis of local news coverage. I also finished an intensive Impact Hub Ticino programme on building a mission-driven startup.
Sole developer and product manager. I took it from concept to a working MVP, then stepped away cleanly when the funding round didn't close, handing the founder the app and the documentation.
My father had the shop and the idea; I moved it to Shopify to get us out of development work and into marketing, then grew it from scratch past CHF 500K+ in sales. I built the price-elasticity and demand-forecasting models behind it, and ran A/B tests that lifted campaign engagement by roughly 70%.
Production ML for the sales and audit teams: recommendation engines and anomaly detection, plus the process automation that clears the busywork around them. Reps were losing up to two hours a day just gathering market data; one recommender took over that watching, worth around four thousand hours a year across the twenty-odd people who used it, by my own estimate. I was Product Owner for a team of five.
Led the AI work under direct VP and CSO sponsorship, and shipped an ML lead-scoring tool across several markets. At the company hackathon, 41 people over two days, our two-person team took third: the smallest team in the field, with an NLP demo for anticipating what customers would need next.
Co-authored a published paper on optimisation under uncertainty, and built the systems around the research: a CNN image classifier served over a REST API, and a 3D drone-trajectory tracker for GPS-denied flight.
I'm open to AI, ML and automation roles around Zurich, Zug and Basel, or remote. Email is the fastest way to reach me.
federico@dignazio.ch