Problem, data, model, deployment, result — written for engineers as much as for recruiters. Each page says exactly what I did myself, and what I would do differently.
Written from projects delivered at thyssenkrupp Automotive, Industrie Saleri Italo and Politecnico di Milano. Confidential details, data and imagery are deliberately omitted.
Semi-supervised vision on the line
A camera system on the assembly line that detects foreign objects and defects in real time, trained semi-supervised because a labelled defect dataset did not — and could not — exist.
5 million datapoints a day
An end-to-end anomaly detection pipeline for manufacturing process data, with an optimisation framework that evaluated 48 000 model variants against performance metrics designed for the actual production question.
Physics and statistics, together
A model that keeps the physical description of the assembly and learns what it cannot capture, reducing scrap and rework rates in assembly operations by 10 %.
Generative AI that stays in the building
A locally hosted retrieval-augmented chatbot over the internal wiki, plus a benchmarking framework to compare LLMs on company-relevant prompts and data rather than on public leaderboards.
Modelling what you do not know
A probabilistic graphical model mapping the dependencies between process parameters, with Monte Carlo simulation used for rigorous uncertainty quantification and robust system optimisation.
Optimisation in the loop with the solver
A global optimisation framework using genetic algorithms, coupling Python directly to Abaqus to automate synthetic data generation and accelerate design convergence.
MSc thesis · peer-reviewed publication
An inverse–direct approach for load and strain monitoring in aeronautical structures, based on a calibration matrix, verified both numerically and experimentally — and published in Structural Control and Health Monitoring.
Industrial AI, manufacturing data, computer vision, generative AI — or anything where engineering and machine learning have to meet in production. If that sounds like your team, I would like to hear about it.
Mauren, Liechtenstein