Skip to content
View AlbertoGiunti's full-sized avatar

Highlights

  • Pro

Block or report AlbertoGiunti

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.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. 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
AlbertoGiunti/README.md

Hi there, I'm Alberto Giunti 👋

🧠 AI & Data Analytics M.Sc. student @PoliTo | 👁️ Computer Vision · 🤖 Robot Learning · 🎮 Reinforcement Learning

🥋 Judo athlete & certified instructor, forged by 16 years on the tatami, following the principle of (柔), the way of flexibility and adaptability

📍 Italy (Prato → Turin)

📧 alberto@giunti.me

GitHub LinkedIn


🔬 What I Do

🎓 M.Sc. in Computer Engineering - Artificial Intelligence & Data Analytics @ Politecnico di Torino (2024 → 2027). I work mainly in computer vision and deep learning (from egocentric video understanding to robotic perception and neuromorphic, event-based vision), and I like taking models out of the notebook and onto real hardware.

My recent work spans spiking neural networks for event-based gesture recognition, vision-based procedural understanding in egocentric video, instance-centric robotic grasping, and reinforcement learning with domain randomization for sim-to-real transfer. Earlier, as a Junior Software Engineer @ Codeguru, I built Python prototypes integrating LLMs into web information-retrieval workflows and shipped front-end interfaces with Vue.js / Nuxt.js.


🛠️ Technical Focus Areas

  • 👁️ Computer Vision & Deep Learning: video understanding, action recognition, event-based / neuromorphic vision
  • 🦾 Robot Learning & Autonomous Systems: ROS2 grasping pipelines, motion planning, sim-to-real transfer
  • 🎮 Reinforcement Learning: policy robustness, domain randomization, SAC / PPO
  • 🤖 LLMs & Applied AI: LLM-powered pipelines for information retrieval and automation
  • 📊 Big Data & Data Analytics: large-scale data processing and analysis
  • 🌐 Full-Stack Development: web applications supporting AI and data systems

🛠️ Tech Stack

Languages

Python C C++ Java Rust JavaScript SQL MATLAB LaTeX Markdown HTML5 CSS3

AI, ML & Computer Vision

PyTorch TensorFlow scikit-learn NumPy Pandas Jupyter Weights & Biases

Robotics & Simulation

ROS Gazebo MoveIt2 MuJoCo

Web & APIs

React Vue.js Nuxt.js Django Node.js Express SQLite REST WebSockets

Tools & Platforms

Linux Git GitHub Docker Arduino Notion

Pinned Loading

  1. instance-centric-grasping instance-centric-grasping Public

    Forked from Fab-Ver/instance-centric-grasping

    "Instance-Centric Grasping" developed for the "Robotics" course @PoliTo. Tech stack: Python

    TeX

  2. project-sim2real-rialti-giunti-gjinaj project-sim2real-rialti-giunti-gjinaj Public

    Reinforcement learning for robotic manipulation in MuJoCo: SAC vs PPO on Gym's Pusher, extended with collision-penalized obstacles, randomized obstacle and goal positions, and density variations. S…

    Python

  3. aml-2025-mistake-detection aml-2025-mistake-detection Public

    Forked from Laio95/aml-2025-mistake-detection

    Advanced Machine Learning course project on CaptainCook4D. Beyond baseline error-recognition classifiers on egocentric cooking videos, a graph-based pipeline reconstructs procedural task graphs: Ac…

    Jupyter Notebook

  4. DSP-exam-call-2 DSP-exam-call-2 Public

    Second call exam — Distributed Systems Programming, Politecnico di Torino @polito (2025/2026). Film Manager app with REST APIs, WebSockets, and MQTT-style Last Will feature.

    JavaScript

  5. SWE-RepetitionManager SWE-RepetitionManager Public

    A Java-based application designed to manage private tutoring sessions and schedules. Developed for the Software Engineering course UNIFI.

    Java