Francesco Forcher

Senior Software Systems Architect and ML Engineer with over 8 years of professional experience, driven by a lifelong passion for programming and mathematics.

Luxembourg, CET

About

I emphasize fast, reliable product development with good attention to detail. Main areas of interest include AI/Machine Learning, Rust, Computer Vision, physics, robotics, High-Performance Computing (HPC), functional programming, distributed systems and databases.

Work Experience

Thales Alenia Space Digital Center of Excellence Luxembourg

2025 - Current

Senior Software Systems Architect, Rust Expert Consultant

Leading the development of a next-generation SDK, orchestration, and ML framework that will enable end-users to access and share On-Board Space Edge Computing hardware platforms through a ultra-low-footprint, reliable, and secure integrated solution.

Stockholm University
Remote

2024 - 2025

Research Assistant, Tech Lead

Coauthor responsible for the AI research and ML engineering side of a research project in computer vision and political economy, led by professors Alex Lee and Per Andersson. We analyze the link between economic development and innovations in art and culture using multimodal AI embeddings to analyze large scale art datasets efficiently, clustering image embeddings in latent space.

Remote

Natzka
Remote

2021 - 2024

AI/ML/Database Developer

Contributed to the design and development of a next-generation OLAP database for data warehousing.

Development of several engine and query language features, such as Boolean formulas and COUNT algorithms, with Rust.
Integration of AI/ML features into the product. Bringing Python and Julia scripts from research prototypes into production-ready containerized microservices, integrating state-of-the-art Gaussian Process based time series forecasting services optimized for low latency.
Worked on a custom Julia distributed logger for observability.
Research on a custom Kubernetes predictive autoscaler for our deployments.
Advanced custom load testing with Grafana k6.
Contributed to database API development, including gRPC and REST API. Implemented different caching and paging mechanisms.

Remote

BLU software

2021

Data Warehouse Consultant

Integration of a PostgreSQL database as data warehouse and its plugin Timescale for fast timeseries inserts and queries.

Used Talend and Airflow for ETL/ELT workloads.
Created interactive forecasts of demand using Facebook's Prophet framework.

CERN

2016 - 2018

Technical Student

I developed advanced statistical routines using Python Pandas and scikit-learn to analyze crystal parameters for CERN's UA9 experiment.

Enabled the analysis of very noisy datasets, with a significant impact in the tender process to award the crystal manufacture contract worth several hundred thousands CHF.
My thesis has been published as CERN internal note.
Using C++ ROOT library, I developed routines to analyze nuclear dechanneling for high energy particle beams in bent crystals, improved the simulation accuracy of SixTrack software.

Education

ETH Zürich

2018 - 2020

Master's Degree in Computational Science and Engineering, Physics minor.

University of Padova

2013 - 2017

BSc in Physics.

Swiss National Supercomputing Centre Summer School

2020

Topic: "Effective High-Performance Computing and Data Analytics with GPUs"

ETH Master Thesis at Paul Scherrer Institut

2020

ETHZ CSE Master Thesis at Paul Scherrer Institut, titled: "Intrusive Uncertainty Quantification of Maps". Developed an application to perform intrusive Polynomial Chaos expansion to quantify uncertainty in simulations based on approximate Hamiltonian maps, using symbolic computation with SymPy, scaled into a distributed process using Dask. A deep learning network approach has been evaluated to speed up the stochastic map calculation.

Skills

Rust
Python
Kubernetes
Machine Learning, AI
Software Architecture and Design
C++
Docker
Data Warehouse
Stochastic Differential Equations

Side projects

Rust implementation of Structured Outputs for LLMs

A highly efficient Rust implementation of the Finite State Machine Indexing algorithm for LLM structured outputs.

Rust
Python

Imaging Time-Series to improve neural network forecasting

Using imaging time series to enhance forecasting results with Neural Networks. The approach has out-performed the pure LSTM architecture by a solid margin within our test datasets.

Deep Learning
Time Series
Convolutional Layers
Matplotlib
Forecasting
Convolutional LSTM
Tensorflow 2
Holt Winters

Uncertainty quantification of Hamiltonian maps using intrusive polynomial chaos expansion

My ETH Zürich Master Thesis titled "Uncertainty quantification of Hamiltonian maps using intrusive polynomial chaos expansion" on the application of intrusive Polynomial Chaos methods to stochastic equations in Hamiltonian mechanics, with application in particle accelerator simulations.

Python

High performance implementation of Density Estimation with Distribution Element Trees

Fast C/C++ implementation of "Density estimation with distribution element trees" (arxiv.org/abs/1610.00345)

C++
R
Matplotlib

Gesture Controlled Robot

An Arduino robot controlled remotely through Bluetooth by the movements of the hands, recognized from an Android application using the OpenCV computer vision library

Android
Arduino
Java
Bluetooth

Sustain-AI

Using ChatGPT-4 API and Pandas to perform sentiment and thematic analysis of text extracted from academic reports.

ChatGPT
API
Pandas
Python
NLP
Thematic Analysis
Sentiment Analysis

Crystal Channeling Analysis

Analysis of channeling in crystals for the purpose of collimation in LHC. Uses Pandas, scikit-learn and C++ ROOT.

C++
ROOT
Python
Pandas
Scikit-learn
Statistical Analysis

Work Experience