Skip to content
View Rasantis's full-sized avatar

Block or report Rasantis

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 supported. This note will be visible to only you.
Report abuse

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

Report abuse
Rasantis/README.md

👋 Hi, I'm Rafael de Santis

AI Engineer • Founder @ ShopGuard AI • Computer Vision and AI Specialist

LinkedIn Email


🧠 About Me

I'm a Brazilian Ai engineer and founder passionate about using AI to solve real-world problems.

  • 🧪 I specialize in computer vision, edge AI, and real-time video analytics.
  • 🏭 I've built CV systems for industrial automation, traffic analytics, facial Recognition and retail security.
  • 🧑‍💻 I’ve worked with top AI companies like Pix Force founded Vision-Labs in the year of 2024 to deliver end-to-end AI solutions for businesses.
  • 🚀 I'm currently building ShopGuard AI, a theft detection platform using computer vision to protect physical retail environments.
  • 💡 I'm a builder — I design, train, deploy, and scale AI systems.

🚨 Current Project – ShopGuard AI

ShopGuard AI is a computer vision platform that detects theft and suspicious behavior in retail stores using real-time video analytics.

  • 👁 Detects concealed items, unpaid exits, and staff fraud
  • 📲 Sends real-time alerts via dashboard & mobile
  • 🛍 Targeting SMBs to enterprise retail chains

Retailers lose $100B+/year to theft — we're fixing that with real-time AI.


🧪 Experience

🧠 AI Engineer @ Pix Force

(2022–2023 | São Paulo, Brazil)
Developed and deployed real-time computer vision models for:

  • 🚗 Traffic analytics (vehicle counting, flow analysis)
  • ⚙️ Industrial automation (defect detection, pattern recognition)
  • 🧠 Optimized YOLOv11 with TensorRT on multi-GPU clusters

🧠 Co-Founder @ Vision-Labs

(2021–2022)
AI services company focused on building CV and automation solutions:

  • 🛠 Delivered projects from automation scripts to real-time CV systems
  • 🤖 Served companies in many diferent industries such retail, industry, logistics, health.
  • 🧩 Built complete pipelines: data prep → training → deployment.

🧠 Technical Stack

🔬 Artificial Intelligence & ML

Python PyTorch TensorFlow OpenCV YOLO TensorRT


🖥️ Backend & APIs

FastAPI Flask Node.js PostgreSQL


🎨 Frontend

HTML5 CSS3 JavaScript React


☁️ Cloud, DevOps & Infra

Docker GitHub Actions AWS GCP Linux


🤖 Automation & Hardware

Jetson Raspberry Pi Node-RED


📊 GitHub Stats


📂 Highlighted Projects

Project Description
🛍 ShopGuard AI Theft detection platform using real-time computer vision on edge devices.
🚗 Traffic Analytics System YOLOv11 + DeepSort model for vehicle counting and tracking in smart cities.
🧪 Vision-Labs Solutions Multiple client-facing AI tools for logistics, retail, and automation.

🧭 What’s Next?

I'm building my own product with ShopGuard AI and seeking to scale it through Y Combinator.
If you're a founder, investor, or engineer interested in vision AI or automation — let's connect!

🚀 Thanks for visiting. Let’s build the future with AI! 🚀

Popular repositories Loading

  1. landing-page-plr landing-page-plr Public

    repositório para venda de produto plr de emagrecimento

    JavaScript 2

  2. AYSNC-MULTITHREADING- AYSNC-MULTITHREADING- Public

    SUPER OTIMIZAÇÃO DE VELOCIDADE, PROCESSANDO O EQUIVALENTE A 150 FPS COM THREAD ATIVADA.

    Python 2

  3. REPOSIT-RIO-IC-AGROTECH REPOSIT-RIO-IC-AGROTECH Public

    C++ 1 2

  4. Auto-GPT Auto-GPT Public

    Forked from Significant-Gravitas/AutoGPT

    An experimental open-source attempt to make GPT-4 fully autonomous.

    Python 1

  5. StoreGuard StoreGuard Public

    Real-Time Shoplifting Detection with Computer Vision

    C# 1

  6. GIT-Exericio GIT-Exericio Public

    Forked from kenjimaeda54/GIT-Exericio

    Praticando GIT

    HTML