Skip to content
View Keyvanhardani's full-sized avatar
🎯
Focusing
🎯
Focusing
47 followers · 43 following

Achievements

Achievement: Pair Extraordinairex4Achievement: Galaxy Brainx4Achievement: Starstruckx2Achievement: Pull Sharkx3Achievement: Public SponsorAchievement: YOLOAchievement: Quickdraw

Achievements

Achievement: Pair Extraordinairex4Achievement: Galaxy Brainx4Achievement: Starstruckx2Achievement: Pull Sharkx3Achievement: Public SponsorAchievement: YOLOAchievement: Quickdraw

Highlights

Block or report Keyvanhardani

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
Keyvanhardani/README.md

Keyvan Hardani

Lead AI Engineer · Doctoral Researcher (PhD) 🇩🇪 Munich, Germany · IEEE Member

TU Darmstadt — PhD: AI for Engineering Systems & Intelligent Document Processing ZM-I Group — Lead AI Engineer (AI-driven platforms for engineering & industrial applications) M.Sc. Cybersecurity (HDBW Munich) · OSCP · CEH · 10+ CVE credits

Research Focus

  • Intelligent Document Processing (OCR, Layout Analysis, Vision-Language Models)
  • AI for Engineering & Infrastructure Systems (technical documents, maps, plans)
  • Agentic AI Systems & LLM-based Automation
  • Privacy-aware & Trustworthy Machine Learning (GDPR-compliant pipelines)
  • Robustness & Security of Applied Machine Learning

🆕 Recently shipped — German-OCR-3 v0.2 (Apr 2026)

Deutsche Vision-OCR. Kompakt (1.0 / 2.7 GB), lokal lauffähig, Apache 2.0. Auf 200+ echten anonymisierten deutschen Rechnungen: 100 % gültiges JSON · 95 % Sender korrekt · 0 % Halluzination.

Current Projects

Stack

Languages · Python · C++ · Go · TypeScript · SQL ML / AI · PyTorch · TensorFlow · ONNX · Transformers · PEFT/LoRA · vLLM · llama.cpp · Ollama Agentic / LLM · LangChain · RAG (Weaviate / FAISS / Pinecone) · Prompt Engineering · Fine-tuning (QLoRA / LoRA) Infra · Docker · FastAPI · CUDA · GPU orchestration · CI/CD · MLOps Security · OSCP mindset · LLM red-teaming · GDPR-compliant pipelines

Contact

📧 hardani@hotmail.de 🔗 LinkedIn 🤗 HuggingFace 🦙 Ollama 🌐 keyvan.ai · german-ocr.de

Open to selected collaborations in applied AI, vision-language systems, and ML infrastructure.

Pinned Loading

  1. german-ocr german-ocr Public

    German-OCR is specifically trained to extract text from German documents including invoices, receipts, forms, and other business documents.

    Python 76 5

  2. Python-Acoustic-Echo-Cancellation-Library Python-Acoustic-Echo-Cancellation-Library Public

    This project implements adaptive filter algorithms for **Acoustic Echo Cancellation (AEC)** and general audio processing,

    Python 22 5

  3. AI-Driven-SIEM-Realtime-Operator-with-Groq-Integration AI-Driven-SIEM-Realtime-Operator-with-Groq-Integration Public

    This project is an AI-powered Security Information and Event Management (SIEM) system designed for real-time threat detection and response. Using Convolutional Neural Networks (CNN), Natural Langua…

    HTML 21 5

  4. Autonomous-Xgo-Dog-Robot-Controller Autonomous-Xgo-Dog-Robot-Controller Public

    The Autonomous Xgo Dog Robot Controller is a sophisticated software system that enables an Xgo robotic dog to autonomously navigate and interact with its environment. Leveraging advanced object det…

    Python 13 4

  5. WordPress-Streamlit-Integration WordPress-Streamlit-Integration Public

    This project provides a WordPress plugin and accompanying Streamlit code that enables user authentication in Streamlit applications using JSON Web Tokens (JWT) from a WordPress server. With this in…

    PHP 15 5

  6. xgo2-robot-eye-and-mouth xgo2-robot-eye-and-mouth Public

    Open-source code for animating the eyes and mouth of the XGO2 robot. Enhances interactive capabilities with lifelike expressions synchronized with spoken words

    Python 11 3