Skip to content
View AbdelrhmanEbied's full-sized avatar

Block or report AbdelrhmanEbied

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
AbdelrhmanEbied/README.md

Hi, I'm Abdelrhman Ebied

I'm just a guy who loves learning, building things, and continuously improving my skills.

I enjoy exploring Machine Learning, Artificial Intelligence, MLOps, Software Engineering, and Mathematics, and I'm always looking for opportunities to learn something new.

I also enjoy building end-to-end applications independently, from designing the system and writing the code to testing, containerizing, deploying, and monitoring it.

My goal is to continuously improve my engineering fundamentals and build increasingly reliable, scalable, and production-ready systems.


Tech Stack

Programming Languages

  • Python
  • SQL
  • Bash

AI Engineering

LLM / RAG

  • LangChain
  • LangGraph
  • LangSmith
  • Hugging Face ecosystem
  • Qdrant
  • Pinecone
  • ChromaDB
  • RAG
  • FastAPI
  • Streamlit
  • Axolotl
  • Unsloth
  • LLaMA-Factory

Databases & Data

  • PostgreSQL
  • Redis
  • SQLite
  • SQLAlchemy

Machine Learning Engineering

  • Scikit-learn
  • NumPy
  • Pandas
  • Matplotlib
  • Seaborn
  • PyTorch
  • SymPy
  • SciPy

MLOps / DevOps

  • Docker
  • Kubernetes (K8s)
  • AWS
  • Git
  • GitHub
  • GitHub Actions
  • CI/CD
  • DVC
  • MLflow
  • Grafana
  • Prometheus
  • vLLM

What I Can Build

I focus on building complete systems rather than only individual components.

I can work independently across the development lifecycle:

Design → Development → Testing → Containerization → CI/CD → Deployment → Monitoring

This includes building end-to-end AI/ML applications, RAG systems, APIs, ML workflows, data pipelines, and production-oriented infrastructure.


Featured Projects

A local-first AI research assistant with streaming chat, hybrid RAG, agent workflows, document search, and a production-oriented FastAPI backend.

A 1B-parameter language model inspired by modern architectures such as Kimi and DeepSeek, built with native PyTorch and designed as a Hugging Face-compatible model.

A lightweight Mixture-of-Experts language model built from scratch in native PyTorch and trained end-to-end on Kaggle using 2× NVIDIA T4 GPUs.

A no-code ML platform for tabular model training with dataset management, preprocessing pipelines, hyperparameter configuration, experiment tracking, data versioning, and model prediction.

A distributed social platform built to explore microservices, Kubernetes, Terraform, AWS infrastructure, event-driven architecture, observability, and load testing.


GitHub Contributions


Currently Learning

I'm continuously expanding my knowledge across:

AI Engineering · Machine Learning · MLOps · Kubernetes · Cloud Infrastructure · Distributed Systems · Software Engineering · Mathematics


Philosophy

Learn continuously. Build things. Understand the fundamentals. Improve every day.


Profile views

Pinned Loading

  1. Tiny-MoE Tiny-MoE Public

    Tiny-MoE is a lightweight Mixture-of-Experts language model built entirely from scratch in native PyTorch and trained end-to-end on Kaggle using free 2× NVIDIA T4 GPUs. The project implements moder…

    Python 20 1

  2. research-assistant research-assistant Public

    A local AI research assistant with streaming chat, Hybrid RAG, and document search.

    Python 6

  3. Chirp Chirp Public

    AWS EKS deployment of an 11-service Twitter-like platform — Terraform, Kubernetes, CI/CD automation, and distributed systems architecture

    Python 1

  4. PyTrain PyTrain Public

    A platform to train and experiment with machine learning models from the UI. For beginners who don't know how to code — and for anyone who wants to run lots of experiments with different models eas…

    Python 1

  5. Tiny-K3 Tiny-K3 Public

    Tiny-K3 — a 969M-parameter (297M active) decoder-only language model built from scratch, combining MLA latent attention, Stable LatentMoE with Quantile-Balancing routing, and Attention Residuals. T…

    Python 2