Skip to content
View pierGit7's full-sized avatar

Block or report pierGit7

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
pierGit7/README.md

Hi there πŸ‘‹, I'm Pier Francesco Sorgiovanni

Software engineer in Copenhagen.

  • πŸ”­ I'm currently working at WSAudiology as a Student Programmer, focusing on DevOps and AI tooling
  • πŸ“š I'm pursuing an MSc in Computer Science and Engineering at DTU
  • 🚀 I'm on the software team of Float Forward DTU: Building simulation environment and AI monitoring dashboard (repo)
  • πŸ›°οΈ Previously: HMI software at Same Deutz-Fahr and satellite test tooling at Thales Alenia Space
  • πŸ“« How to reach me: sorgiovanni60@gmail.com

Connect with me:

LinkedIn

Languages and Tools:

go python csharp dot-net cplusplus c typescript react flask terraform ansible docker azuredevops githubactions grafana nginx linux

Featured projects:

  • πŸ₯— Macros: self-hosted app to plan meals around daily macronutrient targets. Set your weight and daily protein, carbs and fats, pick a recipe for each meal, and the app works out how many grams of each ingredient to eat to hit that meal's targets; log extras and see the kcal left for the day.
    Go REST API with a non-negative least-squares portion solver, static HTML/JS frontend behind nginx, Docker Compose, running on a Raspberry Pi; CI/CD with GitHub Actions builds arm64 images to GHCR and deploys over Tailscale.
  • ⚽ Foosball DTU (contributor): foosball has been my passion since I was a kid, so I joined this ELO ranking app for the foosball players at DTU, made to finally settle who the GOAT is (live site).
    I helped redesign the UI and the ELO rating logic, and developed the new backend deployment on a local server. Go (Gin) REST API with Supabase auth, React + TypeScript + Tailwind frontend on GitHub Pages, Docker images on GHCR deployed with GitHub Actions.
  • 🎨 Chromify: brings black-and-white photos back to life. Upload a grayscale image and a U-Net + GAN model (PyTorch) returns a colorized version.
    Full MLOps pipeline: FastAPI inference service, React/TypeScript frontend, Docker, data versioning with DVC on Google Cloud Storage, container builds on Google Cloud Build and CI with GitHub Actions.
  • 🎯 TrackShot: real-time ball detection and tracking on the edge. A custom-trained YOLOv8n model, INT8-quantized to TensorFlow Lite, runs directly on an ESP32-S3 microcontroller, reading frames from its onboard camera.
    Training with Ultralytics + Hydra configs; on-device inference in C++ with ESP-IDF and TFLite Micro.

Pinned Loading

  1. macros macros Public

    Go

  2. Chromify Chromify Public

    Forked from MarlonBando/Chromify

    Python

  3. CNN-JEPA CNN-JEPA Public

    Forked from kaland313/CNN-JEPA

    Official implementation of our paper "CNN-JEPA: Self-Supervised Pretraining Convolutional Neural Networks Using Joint Embedding Predictive Architecture"

    Jupyter Notebook

  4. TrackShot TrackShot Public

    C

  5. Float-Forward-Autonomous-Team/FloatForwardROS2 Float-Forward-Autonomous-Team/FloatForwardROS2 Public

    Python