~/portfolio $ whoami 

Available for AI engineering roles

Abdullah Ibrahim

AI Engineer · M.Sc. Artificial Intelligence, Cairo University

I ship production AI systems across Computer Vision, NLP, and Generative AI, from data and model development to Dockerized deployment on AWS. My focus is RAG systems, agentic multi-agent workflows, and getting research-grade models into dependable production.

4
applied AI roles across CV, NLP & GenAI
Top 6
ECPC national rank, 3 years running
100+
students mentored in AI & robotics

about

Engineer, researcher, ex-competitive programmer

I'm an AI Engineer who builds end-to-end systems: data pipelines, model development, evaluation, and production deployment. Recent work spans RAG chatbots, agentic multi-agent workflows (ReAct, LangGraph), OCR-plus-LLM document extraction, and ensemble forecasting models delivered to real clients, including four Jordanian public universities.

My core stack is Python, PyTorch, TensorFlow, LangChain, LangGraph, Hugging Face, FastAPI, and Docker, working with both open and proprietary LLMs (GPT, Mistral, LLaMA, Gemma) through fine-tuning, prompt engineering, and API integration. I'm currently pursuing an M.Sc. in Artificial Intelligence at Cairo University.

Before AI engineering, I spent three years as a competitive programmer, ranking in the top 6 nationally at the Egyptian Collegiate Programming Contest. That's where my instinct for algorithms and problem-solving under pressure comes from. I'm most interested in agentic systems, retrieval-grounded LLMs, and MLOps on AWS (Bedrock, SageMaker).

education

M.Sc. Computer Science, Artificial Intelligence
Cairo University, Faculty of Computers & Artificial Intelligence
Jan 2026 – Present · Expected 2028
Artificial Intelligence Program (DEY), 95%
National Telecommunication Institute (NTI) — ML, Deep Learning, Model Evaluation & Optimization
Apr 2025 – Jul 2025
B.Sc. Computer Science, Grade: Good
Al Obour High Institutes · Graduation Project: Excellent
Sep 2019 – May 2023

skills

Technical stack

Languages

PythonSQLC++

Machine Learning & Deep Learning

Computer VisionNLPGenerative AITime-Series ForecastingFeature EngineeringModel Evaluation & Optimization

LLMs & Generative AI

RAGAgentic AIReActLangGraphGPTMistralLLaMAGemmaPrompt EngineeringFine-Tuning

Frameworks & Libraries

PyTorchTensorFlowscikit-learnHugging FaceLangChainPandasNumPy

Deployment & Serving

FastAPIDjangoStreamlitDockerREST APIsMicroservices

Cloud & MLOps

AWS BedrockSageMakerS3EC2LambdaGit / GitHubCI/CDPostmanAgile

Vision & Data Tooling

OpenCVYOLOv8EasyOCRChromaDBSHAPMFCC / Audio Features

experience

Where I've worked

Applied AI Engineer Intern · Helm AI
May 2026 – Present · Remote
  • Build AI product features for enterprise clients, including SVD-based semantic recommendation engines, knowledge-base pipelines, and analytics solutions.
  • Design and ship scalable backend APIs with Python, FastAPI, Django, and Docker, partnering directly with clients to deliver production-ready AI applications.
AI Engineer Intern · Elevvo Tech
Feb 2026 – Apr 2026 · Cairo
  • Built a music-genre classification system from MFCC audio features, owning the full ML lifecycle (preprocessing, feature engineering, training, evaluation, optimization) with scikit-learn and TensorFlow.
  • Developed a time-series sales-forecasting model that turned historical trends into interpretable, decision-ready outputs.
  • Delivered a CNN-based traffic-sign recognition system for real-time classification, containerized for reproducible deployment.
AI Engineer Intern, Digital Transformation · GlobalCorp For Financial Services
Jul 2025 – Oct 2025 · Cairo
  • Owned end-to-end design of AI solutions across NLP, Computer Vision, and Generative AI in an R&D environment, translating business requirements into technical architectures with cross-functional teams.
  • Built OCR-plus-LLM pipelines (LLaMA Vision, EasyOCR, YOLOv8) to extract structured data from unstructured financial documents, deployed in Dockerized production environments.
  • Developed a RAG enterprise chatbot (ChromaDB vector store, CrossEncoder re-ranking, LangChain) for accurate, context-aware retrieval from internal document repositories.
  • Integrated computer-vision models and automated validation workflows into internal platforms, reducing manual processing overhead.
Technical Programs Manager, AI & Robotics · Al Obour High Institute
Dec 2024 – Jun 2025 · Cairo
  • Led an ROV team building ML-based object detection and autonomous navigation, managing project roadmaps and stakeholders in an Agile environment.
  • Mentored 100+ students across AI, robotics, and software engineering through structured learning pathways and knowledge-sharing sessions.

selected work

What I've built

// production & research

01

BoudyPilot — Agentic AI Assistant

A ReAct multi-agent system on Mistral and LangGraph orchestrating 5+ tools (web search via Tavily, email via SendGrid, memory) with dynamic tool selection. Reached ~40% fewer steps to task completion versus a single-agent baseline and sub-3s average latency, shipped as a containerized 3-service Docker deployment.

LangGraphMistralReActDocker
02

Cancer Mutation Analysis

M.Sc. Research · Bioinformatics & ML

End-to-end pan-cancer classification on TCGA somatic-mutation data (MAF), building a patient × gene binary mutation matrix with tumor-mutational-burden features across 33 cancer types. Applied SMOTE, XGBoost/Random Forest with SHAP explainability, and per-class Youden threshold tuning, served through a Streamlit front-end.

XGBoostSHAPSMOTEBioinformatics
03

OLLIE — Enterprise RAG Chatbot

GlobalCorp · Oct 2025

Production RAG chatbot over a large internal knowledge base using LLaMA 3.2, ChromaDB embeddings, and CrossEncoder re-ranking for precise enterprise Q&A. Automated the ingestion, chunking, and embedding pipeline and deployed it via FastAPI and Docker with CI/CD-ready containerization.

RAGLLaMA 3.2ChromaDBFastAPI
04

Bank Statement Analyzer

GlobalCorp · Oct 2025

Generative-AI document analyzer using LLaMA 3.2 Vision and EasyOCR to extract structured financial fields (account, amount, date, currency) from statement images into standardized JSON, with a FastAPI backend handling validation and downstream system integration.

LLaMA VisionEasyOCRFastAPIDocument AI
05

Personal ID OCR System

GlobalCorp · Sep 2025

Production OCR pipeline that extracts structured data from identity documents, combining YOLOv8 for field detection, EasyOCR for text extraction, and LLaMA Vision for post-processing and correction. Fully Dockerized for scalable, reproducible deployment.

YOLOv8EasyOCRLLaMA VisionDocker

// more projects

Obesity Risk Prediction

XGBoost multi-class classifier estimating obesity level from demographics and lifestyle habits, with real-time interactive predictions and model explanations in Streamlit.

XGBoostHealthcareStreamlit

Heart Failure Prediction

Clinical ML model trained on blood pressure, cholesterol, and ejection-fraction data to estimate heart-failure risk, built to support early, data-driven screening.

ClassificationClinical DataStreamlit

Customer Segmentation

K-Means segmentation app where users choose features, find the optimal cluster count via the elbow method, and explore group profiles with auto-generated summaries.

K-MeansClusteringStreamlit

Face Recognition Attendance

Real-time attendance tracking using FaceNet embeddings and OpenCV with database logging, eliminating proxy attendance through automated face detection and identification.

FaceNetOpenCVComputer Vision

AI Translator — Neural Machine Translation

Sequence-to-sequence LSTM encoder-decoder in TensorFlow that compresses source text into a context vector and decodes the target language word by word from bilingual training data.

TensorFlowLSTMSeq2SeqNLP

recognition

Awards & competitions

Competitive Programming
Egyptian Collegiate Programming Contest

Ranked 6th nationally in three consecutive years (2020, 2021, 2022), demonstrating strong algorithmic problem-solving under pressure.

Robotics · Team Leader
MATE Egypt ROV & Underwater Robotics

AI & Robotics leader of the OI ROV Team: 3rd place (2023), 6th place (2024 & 2025), and the No Pain No Gain Award (2022) at the national competitions.

contact

Let's build something.

Open to AI engineering roles, collaboration, and project inquiries. If you have an idea or just want to connect, reach out.