Skip to content
View Ammar-Alnagar's full-sized avatar
🎰
Deciphering the GPU manuscript.....
🎰
Deciphering the GPU manuscript.....

Block or report Ammar-Alnagar

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
Ammar-Alnagar/README.md

👋 Ammar Alnagar

LLM Systems Engineer building production-grade AI infrastructure in Cuda & Python

Currently: M.Sc. AI Student | Specializing in scalable inference engines & advanced RAG systems

LinkedIn HuggingFace Email GitHub


💻 Core Stack

Languages
Rust Python C++

AI/ML
PyTorch Transformers LangChain vLLM

Infrastructure
Docker AWS FastAPI


🎯 Focus Areas

  • 📚 Graph-based RAG with advanced reranking strategies
  • 🤖 Multi-agent orchestration with LangGraph & CrewAI
  • LLM optimization via quantization, distillation & efficient fine-tuning
  • 🔬 RLHF pipelines for specialized domain models

🌐 Open Source Contributions

Active on HuggingFace sharing:

  • Fine-tuned LLM configurations
  • RAG system implementations & benchmarks
  • Optimized inference setups for production use

Explore my repositories for practical implementations of cutting-edge AI research.


📦 Extended Tech Stack (Click to expand)

LLM & Training

Accelerate TRL Unsloth PEFT

RAG & Agents

Haystack Qdrant LangGraph CrewAI

Inference & Serving

Ollama TorchScript ONNX

Databases

Neo4J PostgreSQL Redis


📫 Let's Connect

Open to collaborating on:

  • Open-source AI infrastructure projects
  • Research in efficient LLM systems
  • Production-grade RAG implementations

Reach out: [email protected]


"Optimizing AI systems one inference at a time."

Profile Views

Pinned Loading

  1. Pyron Pyron Public

    Pyron is a Python-based agentic pipeline framework that allows a team of AI agents to work together to complete tasks. It is built using the Google Agents Development Kit and is designed to be easi…

    Python

  2. Rust-Coder-CLI Rust-Coder-CLI Public

    A powerful terminal-based coding assistant that combines the convenience of a modern TUI with the intelligence of large language models. Rust TUI Coder provides an interactive environment where you…

    Rust 13

  3. Ai-Agents.rs Ai-Agents.rs Public

    This project implements a modular multi-agent system in Rust. It demonstrates how agents can communicate, interact, and execute behaviors in a simulated environment. The system is designed to be ex…

    Rust 2

  4. Re-AG-Reasoning Re-AG-Reasoning Public

    ReAG is a Python SDK for building Retrieval-Augmented Generation (RAG) applications. It provides a flexible and easy-to-use client for querying large language models (LLMs) with your own data.

    Python 1

  5. Marla Marla Public

    This project implements an agentic pipeline using the Google Agent Development Kit (ADK) framework. It features a master agent that supervises and delegates tasks to a team of specialized agents, e…

    Python

  6. SLRAG-with-COT SLRAG-with-COT Public

    Self Learning RAG With COT is a project that implements Retrieval-Augmented Generation (RAG) combined with Chain of Thought (COT) reasoning. This project aims to enhance the performance of language…

    Python 17 3