Road 01 — The Mechanical Engineer

I learned the machine before I learned the model.

Seven years of mechanical engineering, four of them standing inside an engine plant. It is the reason I can talk to a process owner about tolerances and tool wear before I talk to anyone about a training set.

I studied industrial engineering in Trento, spent an Erasmus semester at TU Wien, then took a master's in mechanical engineering at Politecnico di Milano specialising in materials and manufacturing. My thesis built a load monitoring system for aeronautical structures — an inverse problem solved with a calibration matrix, verified numerically and experimentally, later published in a peer-reviewed journal.

After graduating I became a resident engineer for Industrie Saleri Italo, embedded at the BMW Motoren plant in Steyr. Thermal management solutions and water pumps, from first concept through to series production — and everything that comes with that: quality escalations, supplier negotiations, failure analysis with the customer's own team, all of it in German and English.

That is where I learned the thing that now shapes every ML project I run: data from a factory is a physical artefact. It has a fixture, a calibration, a shift pattern and a person who entered it. If you do not know how a measurement was produced, you do not know what your model learned.

Degrees
MSc PoliMi · BSc Trento
Industry
Automotive · Aerospace
Plant
BMW Motoren, Steyr
Products
Thermal management, water pumps
Capabilities

What the engineering half covers

01

Design & simulation

Mechanical design backed by analysis rather than by precedent — and enough FEM to know when the analysis is lying to you.

  • Mechanical design
  • CAD
  • FE modelling
  • Structural analysis
  • Topology optimisation
02

Manufacturing

Specialised in materials and manufacturing at Politecnico di Milano, then spent four years industrialising products for series production.

  • Advanced manufacturing
  • Industrialisation
  • Metrology
  • Additive manufacturing
  • Laser processing
03

Experiments & measurement

Design of experiments, hypothesis testing and sensor-based measurement. The habit of asking what a number can actually support starts here.

  • Design of experiments
  • Hypothesis testing
  • Sensor instrumentation
  • Load & strain monitoring
Engineering work

Projects on this road

Case studies where the physics does real work — simulation in the loop, inverse problems, and models built on top of a physical description rather than instead of one.

01 2024 — 2025 · Precision assembly

Physics and statistics, together

Hybrid Physics / Data-Driven Assembly Model

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 %.

RegressionHybrid ModellingProcess Optimisation
Scrap & rework
−10 %
Formulation
Physics + ML
Model search
AutoGluon
Fallback
Physical model
Read the case study
02 2024 · Process understanding

Modelling what you do not know

Bayesian Network for Uncertainty Quantification

A probabilistic graphical model mapping the dependencies between process parameters, with Monte Carlo simulation used for rigorous uncertainty quantification and robust system optimisation.

Probabilistic ModellingUncertainty QuantificationOptimisation
Model
Bayesian network
Sampling
Monte Carlo
Output
Full distributions
Use
Robust optimisation
Read the case study
03 2023 — 2024 · Design optimisation

Optimisation in the loop with the solver

Genetic Algorithms Coupled to FEM

A global optimisation framework using genetic algorithms, coupling Python directly to Abaqus to automate synthetic data generation and accelerate design convergence.

OptimisationSimulationMechanical Design
Solver
Abaqus FEM
Search
Genetic algorithm
Data
Synthetic, automated
Goal
Faster convergence
Read the case study
04 2019 — 2020 · Structural health monitoring

MSc thesis · peer-reviewed publication

Load Monitoring for Aeronautical Structures

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.

Structural AnalysisInverse ProblemsExperimental Validation
Publication
SCHM journal
Method
Inverse–direct
Verification
Numerical + experimental
Thesis grade
110/110
Read the case study
Experience

Four years inside an engine plant

Nov 2019 — Jun 2023 Steyr, Austria & Lumezzane, Italy

Resident Engineer — R&D

Industrie Saleri Italo, at BMW Motoren

  • Resident engineer at the BMW Motoren plant in Steyr, developing automotive products from first concept to series production.
  • Responsible for the design and industrialisation of thermal management solutions and water pumps.
  • Supported and reinforced the quality, project management and commercial teams.
  • Built the communication and partnership with the customer and Tier 2 suppliers; moderated weekly team discussions.
  • On-site customer technical support in German and English, including work with the BMW failure analysis team.
Education

Where the engineering comes from

2016 — 2019 Milano, Italy

MSc Mechanical Engineering

Politecnico di Milano

  • Specialisation in materials and manufacturing.
  • Mechanical design, energy systems, measurements, design and analysis of experiments, dynamics and control.
  • Thesis: load monitoring system for aeronautical structures based on a calibration matrix approach.
  • Final evaluation 110/110 · weighted exam average 28.4/30.
2012 — 2016 Trento, Italy

BSc Industrial Engineering

Università degli Studi di Trento

  • Mathematical analysis, physics, materials science, thermodynamics, fluid and solid mechanics.
  • Erasmus+ semester at TU Wien, attending lectures and exams in German and English.
  • Thesis: solid state hydrogen storage systems.
  • Final evaluation 101/110.
The other road

Then the questions became statistical.

Same factory, same processes, different tools. See what happened when I went back to university for a second master's — in artificial intelligence — while working full time.

Take the data science road
Contact

Currently looking for the next problem worth solving.

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.

lucamcwood@gmail.com LinkedIn Instagram CV

Mauren, Liechtenstein