MS AI Student @ UMD | AI Engineer building data driven applications, predictive models, RAG pipelines, LLM-powered systems and AI agents.
- Languages: Python, SQL
- AI & Generative AI: LLMs, RAG, AI Agents, MCP, LangChain, CrewAI, Fine-tuning, LoRA, QLoRA
- Machine Learning: Regression, Classification, Clustering, Deep Learning, Model Evaluation
- Data Science & Analytics: Data Cleaning, EDA, Data Visualization, Statistical Analysis, Feature Engineering
- Backend & APIs: FastAPI, REST APIs, PostgreSQL, Pydantic
- Frameworks & Tools: Pandas, NumPy, Scikit-learn
- Cloud & Deployment: AWS, GCP, Docker, Kubernetes
-
AI Operations Automation Agent – AI-powered operations and procurement automation platform that helps managers ask business questions in plain English and receive KPI, supplier, inventory, spend, and risk insights. Built with FastAPI, PostgreSQL, MCP tools, Slack workflows, scheduled reporting, and a Streamlit dashboard. Deployed on AWS EC2 with Nginx, HTTPS, Cloudflare domain, and secured internal app ports.
- Live Application: https://aiops.moatazai.com/
- GitHub: https://github.com/moatazsaad/ai-operations-automation-agent
-
Legal AI Assistant – End to end deployed RAG system on AWS & GCP for contract Q&A, using embeddings and LLMs with evaluation (Recall@3: 0.95, MRR@5: 0.925) to deliver accurate, explainable answers
https://github.com/moatazsaad/legal-ai-assistant -
HR RAG System – Retrieval based HR assistant for document search and question answering using embeddings and LLMs
https://github.com/moatazsaad/hr-rag-system -
Market Intelligence AI System – Multi-agent system for automated market research and competitor analysis
https://github.com/moatazsaad/autonomous-market-competitive-intelligence-ai-system