Available for opportunities

Hi, I'm Yousef Malak Ibrahim AI Engineer & ML Developer

I build intelligent systems that bridge the gap between cutting-edge AI research and real-world impact. From multi-agent architectures to production-grade ML pipelines, I turn complex problems into elegant solutions.

0+ Projects
0% AI Certification
Yousef Malak Ibrahim
AI Agents
AI Backend
Scroll Down

About Me

Maadi, Cairo, Egypt
Ain Shams University
yousefmalak55@gmail.com
+20 127 541 6149

I'm a passionate AI Engineer and Machine Learning Developer currently pursuing my Bachelor's in Computer Science at Ain Shams University. With a strong foundation in building production-ready AI systems, I specialize in creating intelligent multi-agent architectures, knowledge graphs, and scalable ML pipelines.

Currently working at Wider, a multinational company, where I build and deploy backend AI agent infrastructure handling production authentication flows and semantic metadata enrichment using LLM extraction pipelines.

As Head of AI at iCLUB, I lead strategic AI initiatives, organize workshops on generative AI and model deployment, and mentor the next generation of AI developers.

Languages

Arabic
Native
English
Fluent
German
Good

Achievements & Highlights

2nd Place

ML Project Competition

Ranked 2nd in an ML project at Ain Shams University.

1st Place

NLP Project

Won 1st place for an NLP project at Ain Shams University.

Experience & Education

2025 — Present

AI Engineer

Wider (Multinational Company)

  • Built and deployed backend AI agent infrastructure handling production authentication flows
  • Implemented Knowledge Graph systems with semantic metadata enrichment using LLM extraction pipelines
  • Integrated LangChain-based agents communicating with graph services via REST APIs
  • Collaborated with cross-functional teams on multi-agent system architecture and deployment
2026 — Present

AI Engineer Intern

Kayfa (Multinational Company)

  • Built AI solutions in education and business as part of a multinational team
  • Developed a multilingual LangGraph sales agent with RAG over a 52-course catalog, lead scoring, and WhatsApp notifications via Twilio
  • Built a student analytics dashboard consolidating 7 LMS sources with a 37-issue data-quality audit and Plotly EDA
2024 — Present

Head of AI

iCLUB (Student Club) — Ain Shams University

  • Led strategic AI initiatives and organized workshops on generative AI, deployment, and ethics
  • Mentored members in Python, TensorFlow, and cloud-based ML pipeline development
  • Integrated AI solutions into club-led tech products and demos
2023 — 2027

Bachelor of Computer Science

Ain Shams University — Software Engineering

GPA: 3.5 / 4.0 (A-)

Feb 2026

AI Agent Developer Course

Orange Digital Center

Grade: 99.3% | 30 Hours | AI Agents, LLMs, LangChain, RAG, Multi-Agent Systems

Featured Projects

Sadeed — AI Claim Management System

Multi-agent LangGraph pipeline (Extractor → Investigator → Resolver → Explainer) for automated claim triage and resolution with semantic deduplication using pgvector HNSW indices and multilingual embeddings.

Django LangGraph pgvector Celery Redis Docker
Smart LLM routing via OpenRouter Fraud detection engine Auto-retraining pipeline K-Means clustering analytics

Loom CLI — Multi-Agent Coding Pipeline MIT

Terminal-native multi-agent coding pipeline powered by LangGraph. Splits work across specialized agents (Thinker → Worker → Debugger), each with its own prompt, tools, and model provider. Supports Anthropic, Groq, OpenRouter, and NVIDIA — mix providers mid-session.

LangGraph Python LLM Multi-Agent CLI
Provider-agnostic — swap models mid-session TPM-aware exponential backoff Context compaction keeps token budget SQLite checkpointing for resume

AI Travel Reservation Chatbot

Automated chatbot integrating multiple flight and hotel reservation APIs for real-time booking with workflow automation pipelines using n8n.

n8n API Integration Chatbot
Real-time booking API orchestration

Online Exam Management System

Desktop application for creating and managing exams with automated grading, user authentication, and performance tracking using OOP principles.

Java JavaFX Maven

Land Type Classification — Satellite Imagery

Compared ResNet50 (81.9%) vs EfficientNetB0 (96.3%) on NWPU-RESISC45 dataset for multi-class land cover detection using transfer learning.

Python TensorFlow Sentinel-2
96.3% accuracy achieved

Forest Cover Type Prediction

Multi-class classification using XGBoost achieving 86.6% accuracy with engineered interaction features for improved predictive performance.

XGBoost Classification

Walmart Sales Forecasting

Time series forecasting with LightGBM predicting weekly sales (MAE ≈ $7,277) using rolling averages and TimeSeriesSplit cross-validation.

LightGBM Time Series

Diabetes Prediction Model

Applied SMOTE balancing and trained Logistic Regression, SVM, and Random Forest achieving 76% accuracy for diabetes prediction.

Scikit-learn SMOTE Classification

Mall Customer Segmentation

Segmented customers into 5 clusters via Elbow method with K-Means, visualizing spending vs. income patterns.

K-Means Clustering

Image Segmentation App

Graph-based segmentation with Gaussian smoothing, parallel RGB processing, and multi-format export capabilities.

C# Windows Forms DSU

Kayfa AI Sales Agent Internship

Multilingual (Arabic/English, multi-dialect) LangGraph sales agent that helps prospective students explore a 52-course catalog, qualifies leads with automatic CRM ticket creation, and notifies the sales team on WhatsApp in real time.

LangGraph Python RAG MongoDB Twilio Streamlit Pydantic v2
RAG over 52-course catalog Lead scoring + CRM tickets WhatsApp via Twilio

Kayfa Student Analytics Dashboard Internship

Unified analytics view that consolidated 7 multi-source LMS exports, resolved 37 data-quality issues, and delivered interactive EDA visualizations to surface student engagement and performance trends.

Python Pandas Plotly Jupyter Data Cleaning
7-file LMS consolidation 37-issue quality audit Plotly EDA dashboards

Skills & Technologies

AI & Agents

LangChain LangGraph Multi-Agent Systems RAG Prompt Engineering Knowledge Graphs

Machine Learning

Scikit-learn TensorFlow PyTorch XGBoost LightGBM SMOTE

Backend

Django FastAPI REST APIs Authentication MongoDB Modular Architecture

Data & Vector

pgvector Qdrant Supabase PostgreSQL Redis Celery Docker

Automation

n8n Twilio API Orchestration Chatbot Pipelines Low-Code Workflows

Languages & Tools

Python Java C# C++ JavaScript SQL Pandas Jupyter Streamlit Seaborn

Get In Touch

I'm always interested in hearing about new opportunities, collaborations, or just having a great conversation about AI and technology.