Hi, I'm
Sana M. Araj

AI Engineer building intelligent systems with product strategy and business impact. Specializing in LLMs, RAG systems, and Document Intelligence.

Scroll

About Me

AI Engineer who builds intelligent systems from prototype to production. I specialize in LLMs, RAG systems, and document intelligence — turning complex AI research into scalable solutions that deliver real business impact.

LLMs & RAG

Chatbots, Retrieval Systems,
Document Intelligence

Computer Vision

OCR, Object Detection,
Image Processing

Backend & APIs

FastAPI, Databases,
System Integration

Data & ML

Pipelines, Analytics,
Model Training

// EXPERIENCE

Career Journey

Jun 2025 - Present
Innosoft
Saudi Arabia

AI Engineer

Spearheading R&D for RAG systems and Document Intelligence platform, delivering 40% performance improvements and 60% reduction in manual processing. Contributing to TDF chatbot development and representing AI solutions at industry exhibitions.

LLMs RAG Document AI FastAPI LangChain
Jan 2025 - May 2025
IAU
Khobar, Saudi Arabia

Teaching Assistant

Delivered hands-on workshops on ML algorithms, Python, and NLP for aspiring data scientists. Mentored students on real-world AI projects, guiding architecture and implementation decisions.

Teaching Python ML Algorithms NLP
Jun 2024 - Aug 2024
Innosoft
Saudi Arabia

AI Intern

Developed RAG applications and document processing pipelines with A/B testing for optimization. Gained hands-on experience with LLMs, NLP, and production AI system architecture.

RAG NLP A/B Testing Python
// PROJECTS

Featured Work

// DOCUMENT AI

Document Management System

AI-powered document repository with NER-based entity extraction, intelligent filtering, auto-generated summaries, and a RAG chatbot for natural language queries.

Python spaCy NER FastAPI LangChain RAG PostgreSQL React
// NLP PIPELINE

Resume Analyzer

NLP pipeline that parses resumes into structured data, generates vector embeddings, and enables semantic search for intelligent talent matching via RAG.

Python Transformers Embeddings ChromaDB
// VERIFICATION

DocCheck - Document Verification

Multi-stage document verification using VLMs, OCR, and QR decoding for automated authenticity validation and compliance checking.

VLMs OCR QR Decoding FastAPI
// CONVERSATIONAL AI

TDF Chatbot

RAG-powered conversational AI with dynamic knowledge ingestion, semantic search, and context-aware responses from custom document collections.

LangChain Groq RAG Vector DB
// CLASSIFICATION

DocClassify - Hybrid Classification

Dual-strategy document classifier combining TF-IDF rule-based categorization with LLM-powered semantic classification for intelligent routing.

TF-IDF scikit-learn LLMs FastAPI
// MEDICAL AI

epileptech - Medical AI

Deep learning EEG classification for epileptic seizure detection with GAN-based data augmentation. Clinical research with King Fahd University Hospital.

TensorFlow PyTorch GANs Medical AI
// SKILLS

Tech Stack

AI & Machine Learning

LLMs RAG Systems Document Intelligence NLP Computer Vision OCR Fine-tuning

Frameworks & Tools

LangChain LlamaIndex OpenAI Hugging Face OpenCV Pinecone ChromaDB

Engineering & Data

Python FastAPI PostgreSQL MongoDB Pandas SQL AWS Docker
// EDUCATION

My Education

Imam Abdulrahman Bin Faisal University (IAU)

Bachelor of Science in Artificial Intelligence

Computer Engineering Department

2020 - 2025

4.8/5.0 GPA
First Honor Degree
Khobar, Saudi Arabia
// CONTACT

Let's Build Together

Have an AI Challenge?

I'm always excited about new AI projects and opportunities. Whether you need help with ML strategy, building AI products, or scaling your infrastructure.

sana.majed.araj@gmail.com
LinkedIn
GitHub
Khobar, Saudi Arabia