Francesco Zuppichini
Head Of Growth And Product at roboflow
Lugano, Ticino, Switzerland
Summary
🤩
Rockstar🎓
Top SchoolFrancesco Zuppichini is a Head of Growth and Product and machine learning engineer with a decade of experience specializing in computer vision, deep learning, data analytics and full‑stack development. Educated with a BSc in Informatics and an MSc in Artificial Intelligence, he has shipped production ML systems at Hugging Face, Roboflow, Zurich Insurance and V7, and contributed to high‑visibility projects like the Hugging Face Transformers library (notably MaskFormer and feature extractor fixes). Equally comfortable in product and hands‑on engineering, he pairs growth strategy with model fine‑tuning, custom data pipelines and real‑time analytics. A lifelong tinkerer, his GitHub spans Arduino/Raspberry Pi hardware hacks to advanced vision demos, reflecting a practical curiosity that drives rapid prototyping and robust solutions. Based in Lugano, he mentors, freelance consults and crafts technical content—bringing a rare blend of product intuition and deep technical rigor.
10 years of coding experience
8 years of employment as a software developer
Master's degree Artificial Intelligence, Master's degree Artificial Intelligence at USI Università della Svizzera italiana
klingon
Github Skills (20)
transformers10
pytorch10
feature-extraction10
python10
data-science10
machine-learning10
image-segmentation10
deep-learning10
segmentation10
model-testing10
computer-vision10
integrate9
integrations9
nlpjs9
bert9
Programming languages (22)
Github contributions (5)
huggingface/transformers
Feb 2022 - Apr 2022
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Role in this project:
ML Engineer
ML EngineerContributions:384 reviews, 59 commits, 43 PRs in 1 month
Contributions summary:Francesco primarily contributed to the MaskFormer model, specifically focusing on implementing and testing feature extraction methods and post-processing functionalities. They refactored code, fixed bugs related to the output of post-processing functions, and added tests to ensure the correct behavior of the feature extractor. The user also worked on integrating and testing the Resnet and Swin models.
pythonbertspeech-recognitionstate-of-the-artflax
NielsRogge/Transformers-Tutorials
Feb 2022 - Mar 2022
This repository contains demos I made with the Transformers library by HuggingFace.
Role in this project:ML Engineer
ML EngineerContributions:9 commits, 1 PR, 2 comments in 1 month
Contributions summary:Francesco primarily worked on fine-tuning a MaskFormer model within the repository, demonstrating an understanding of image segmentation and transformers. Their commits involved modifying and creating notebooks focused on downloading, preparing, and fine-tuning the model on a custom ADE20k dataset. The changes included modifying the training loop and data pipelines to suit a custom dataset.
layoutlmpytorchtransformersvision-transformernlp
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.