Skip to content
View youssef-yasser-ali's full-sized avatar
39 followers · 35 following

Achievements

Achievement: Pull SharkAchievement: YOLO

Achievements

Achievement: Pull SharkAchievement: YOLO

Block or report youssef-yasser-ali

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. 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
youssef-yasser-ali/README.md
Typing SVG

LinkedIn Email Kaggle

🚀 About Me

name: Youssef Anwar
location: Cario, Egypt
current_role: Software Engineer & AI Specialist @ TJM Labs
previous_role: AI / Machine Learning Engineer @ IdaamCloud
education: B.Sc. Computer and Control Systems Engineering - Mansoura University (Honors)
passion:
  [
    "Artificial Intelligence",
    "Voice AI",
    "Natural Language Processing",
    "Computer Vision",
  ]
current_focus:
  ["LLM Applications", "Real-Time Voice Pipelines", "RAG Systems", "MLOps & Deployment"]
fun_fact: "Built production voice AI pipelines integrating 10+ STT and 15+ TTS engines!"

I'm a Software Engineer and AI Specialist who loves turning research-grade AI into real, production-ready systems — from real-time voice assistants and multilingual speech pipelines to RAG systems and computer vision applications. I care about deep problem understanding before building, and about shipping AI that actually works at scale.

Featured Projects

Face Re-Identification System Mini-RAG System
Scalable face recognition system supporting multi-project identity matching using DeepFace embeddings and Qdrant vector similarity search, with RESTful APIs for image processing, embedding generation, and real-time search, plus MongoDB metadata storage. Production-ready Retrieval-Augmented Generation system with a modular architecture spanning 7 API endpoints, async MongoDB (Motor), optimized vector search, and multi-provider LLM support (OpenAI, Cohere, Gemini, Ollama).
RAG-Toolkit Library Custom GPT-2 for Code Generation
Open-source Python library for advanced RAG pipelines implementing StepBack, Fusion, and query decomposition strategies, with an embedding-based intelligent query router that improved response accuracy by 35%. Published on PyPI. GPT-2 (124M parameters) implemented from scratch for Python code generation, using gradient accumulation, mixed precision training, and cosine learning-rate scheduling for optimized convergence and domain-specific tokenization.

Technology

Python TensorFlow PyTorch Scikit-Learn OpenCV Hugging Face OpenAI LangChain
LangGraph vLLM Ollama FastAPI Flask Qdrant MongoDB PostgreSQL
Azure AWS Docker Git GitHub Linux Jupyter JavaScript

📈 GitHub Stats

GitHub Streak
Contribution Graph

Ready to turn ideas into reality? Let's connect and create something extraordinary!

Profile Views



Pinned Loading

  1. rag-toolkit rag-toolkit Public

    library designed to streamline the creation of Retrieval-Augmented Generation (RAG)

    Python 4

  2. Brain-Tumor-Detection-System Brain-Tumor-Detection-System Public

    FastAPI project designed for brain tumor classification and segmentation using PyTorch. The project is containerized with Docker and can be deployed.

    Jupyter Notebook 1

  3. CardiAi/Heart-Disease-Model CardiAi/Heart-Disease-Model Public

    full-stack app

    Jupyter Notebook

  4. mini-rag mini-rag Public

    RAG system model for question answering.

    Python