Skip to content
View amrgaberM's full-sized avatar
1 follower · 2 following

Achievements

Achievement: Quickdraw

Achievements

Achievement: Quickdraw

Block or report amrgaberM

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
amrgaberM/README.md

Amr Hassan

Typing SVG

Backend Engineer specializing in production APIs and AI/ML systems.
Cairo, Egypt · Open to remote

LinkedIn Portfolio Email

About

Backend engineer focused on building production-grade APIs and AI systems end-to-end — from architecture to deployment.

  • Reduced PDF processing from 3 minutes to 17 seconds (10x) with 9/10 accuracy using async pipelines and vector search
  • Built a semantic code search system with 85% retrieval accuracy at 38ms latency
  • Trained a 124M parameter Transformer from scratch — 41% validation loss reduction on consumer GPUs
  • Shipped automated PR review agent with sub-200ms end-to-end response via Groq LPU inference

Open to: Backend Engineer · AI Engineer · Python Developer — Cairo or remote

Featured Projects

SmartDoc API — Production RAG

GitHub Demo

Problem: Processing large PDFs for semantic search was slow and inaccurate.
Solution: Async RAG pipeline with sliding window chunking and in-database vector search.
Result: 3min → 17s processing · 9/10 accuracy · 28% accuracy gain over fixed chunking · <5ms search latency

Django Celery PostgreSQL Redis

CodeLens — Semantic Code Search

GitHub Demo

Problem: Navigating large codebases is slow and context is lost.
Solution: Hybrid search combining semantic embeddings with BM25 + AST-based chunking.
Result: 85% retrieval accuracy · 38ms latency · 2,000+ code chunks indexed

FastAPI ChromaDB Python

CodeSense AI — Automated Code Review

GitHub Demo

Problem: Manual PR reviews are slow and miss security vulnerabilities.
Solution: Event-driven agent processing GitHub webhooks with Groq LPU inference.
Result: Sub-200ms end-to-end · automated inline PR comments · real-time bug and vulnerability detection

FastAPI Docker Groq

FabulaGPT — GPT from Scratch

GitHub

Problem: Understanding Transformer internals beyond API calls.
Solution: 124M parameter decoder-only Transformer built in raw PyTorch, no shortcuts.
Result: 41% validation loss reduction (8.56→5.05) · gradient accumulation on dual T4 GPUs

PyTorch CUDA Python

Tech Stack

Backend & APIs
Python Django FastAPI PostgreSQL Redis Celery

AI & ML
PyTorch LangChain ChromaDB Groq

DevOps & Tools
Docker GitHub Actions Linux Nginx

Backend Engineer · AI Systems · Python
Cairo, Egypt · Open to remote opportunities

LinkedIn Portfolio Email

Pinned Loading

  1. smartdoc-enterprise-api smartdoc-enterprise-api Public

    Enterprise-grade Document Intelligence Platform using Django, Celery, Redis, and RAG (LangChain + pgvector).

    Python

  2. codelens-intelligence codelens-intelligence Public

    Production-grade RAG system that understands entire codebases. AST-aware chunking, hybrid retrieval, dependency graphs, and multi-file reasoning for GitHub repositories.

    Python

  3. FabulaGPT FabulaGPT Public

    A high-performance implementation of a GPT-2 architecture optimized for emergent storytelling. Trained on the TinyStories dataset, this project focuses on achieving linguistic coherence and narrati…

    Python

  4. injury-prediction-prevention-ml injury-prediction-prevention-ml Public

    A machine learning system for predicting and preventing athlete injuries using advanced data analysis, risk assessment, and tailored recommendations.

    HTML

  5. codesense-ai codesense-ai Public

    AI-powered code review tool with CLI, REST API, and GitHub integration

    Python

  6. GPT-Implementation GPT-Implementation Public

    Research code implementing the "Attention Is All You Need" architecture. Engineers a stable training loop for a 163M LLM using reduced-precision techniques on free-tier compute.

    Jupyter Notebook