I'm a Generative AI Engineer with a B.Sc. in Artificial Intelligence & Data Science from Beni-Suef National University (graduation project scored A+ / 99%). I work across the full AI product lifecycle — from fine-tuning and RAG pipeline design to shipping production backends that actually serve the models. I like taking an idea from a research notebook all the way to a deployed system someone can actually use, and I validate what I build empirically rather than just shipping it and hoping.
- 🔭 Currently a Backend AI Engineer Intern at FlyRank AI, and a Multimodal AI Engineer & Researcher with the NAMAA Community
- 🚀 Founder of CadArena — an LLM-to-CAD platform that cut design time by an estimated 85–90% vs. manual drafting
- 🧠 Focused on LLMs, RAG, agentic systems, and vector search, deployed with FastAPI, Docker, and modern full-stack tooling
- 🧪 Background across ML, Computer Vision, and NLP applied-research tracks (NTI), plus data engineering internships at Huawei and Microsoft DEPI
- 🌍 Bilingual (Arabic/English) — freelance AI/LLM instructor for online learners
- 🛰️ Participant, NASA Space Apps Challenge 2025
- 📫 Reach me at ytaha8586@gmail.com
- Building and evaluating production-grade RAG pipelines with real retrieval metrics, not just demos
- Fine-tuning LLMs (LoRA/PEFT) for domain-specific tasks, including an Arabic OCR fine-tuning project on TrOCR
- Multi-agent workflows and tool-use patterns for agentic AI systems
- Strengthening data structures & algorithms and system design fundamentals
| Area | Examples |
|---|---|
| GenAI & LLMs | RAG pipelines, LLM fine-tuning (LoRA/PEFT), prompt & context engineering, multi-agent systems |
| Backend Engineering | FastAPI services, PostgreSQL/SQLAlchemy schemas, WebSockets, JWT auth, Docker deployments |
| NLP | Text classification, NER, information extraction with Hugging Face Transformers |
| Vector Search | Qdrant, pgvector, FAISS — semantic search & retrieval for RAG systems |
| Full-Stack | Next.js/React frontends wired to LLM-powered backends |
| Role | Organization | Period |
|---|---|---|
| Backend AI Engineer Intern | FlyRank AI (Remote) | Jun 2026 – Present |
| Multimodal AI Engineer & Researcher | NAMAA Community (Remote) | Jun 2026 – Present |
| Founder & AI Engineer | CadArena | Sep 2025 – Jun 2026 |
| AI/ML Intern — ML, CV & NLP Tracks | National Telecommunication Institute (NTI) | Dec 2024 – Sep 2025 |
| AI & LLMs Instructor (Self-Employed) | Remote | Oct 2025 – Nov 2025 |
| Big Data Engineer Intern | Huawei, Shebin El Kom | Aug 2025 |
| Data Engineer Trainee | Digital Egypt Pioneers Initiative (DEPI) | Jun 2024 – Sep 2024 |
| AI Fundamentals Trainee | Zewail City of Science and Technology | Aug 2023 – May 2024 |
CadArena — LLM-powered natural language → CAD (DXF) platform. Converts plain-English engineering commands into valid, parametric CAD drawings. Graduation project, scored A+ (99%). Python · FastAPI · PostgreSQL · WebSockets · Next.js · Ollama
NutriAI — End-to-end RAG nutrition assistant: ingestion, semantic chunking, embeddings, vector search, and grounded LLM Q&A. FastAPI · Qdrant/pgvector · Docker
AI Codebase Understanding Engine — Generates architecture summaries and an interactive dependency graph for any public GitHub repo, plus a RAG-powered chat to query the codebase.
PharmaSaaS — Multi-tenant pharmacy management platform with branch-level data isolation. FastAPI · React 19 · PostgreSQL
Aether Analytics — Built for NASA Space Apps Challenge 2025: automated retrieval, cleaning, and visualization of NASA earth/space datasets.
Speech Emotion Recognition — CNN-based pipeline classifying emotional states from audio using MFCC/spectrogram feature engineering. Python · CNNs · Hugging Face
CadArena DXF Viewer — Companion tool for CadArena to render and inspect generated DXF drawings.
B.Sc. in Artificial Intelligence & Data Science Faculty of Computers & Artificial Intelligence, Beni-Suef National University — Oct 2022 – Jul 2026
- Graduation Project: CadArena — end-to-end Generative AI platform translating plain-English engineering commands into precise CAD drawings (DXF) using LLMs. Score: A+ (99%)
- Relevant Coursework: Machine Learning, Deep Learning, Natural Language Processing, Computer Vision, Data Structures & Algorithms
- Building LLM Applications With Prompt Engineering — NVIDIA
- NVIDIA DLI — Generative AI Summer Training Program
- AI for All: From Basics to GenAI Practice — NVIDIA
- Supervised Machine Learning: Regression and Classification — Stanford & DeepLearning.AI
- Oracle Cloud Infrastructure 2025 Certified AI Foundations Associate
- Microsoft Data Engineer — Digital Egypt Pioneers Initiative (DEPI)
- Huawei Big Data Associate
- NASA Space Apps Challenge 2025 — Certificate of Participation

