I build production GenAI systems (RAG, agents, fine-tuning) — and document the path from AI grad to AI Engineer, in Arabic and English.
🎓 B.Eng. Information Engineering (AI & Data Science), Syrian Private University 💼 AI Engineer @ AppTech Systems
adstyle — AI marketing-image generator: turns a product photo into a finished ad while keeping the product pixel-perfect.
Inpaint-around-product + custom SDXL LoRA + LLM art director. Bilingual (Arabic/English).
pixel-exact product · 1,253-img LoRA · CLIP 32.6 / FID 227 · SDXL + PEFT + FastAPI
Agent From Scratch — Tool-calling data-analysis agent built with no framework Raw ReAct loop, 9 tools, evaluated on clean and adversarial data. 95.8% held-out · 66.7% dirty data · 100% abstention · Groq + gpt-oss-120b
AI Career RAG — Bilingual (Arabic/English) RAG career assistant
Grounded retrieval + generation, evaluated systematically — not a chatbot wrapper.
Precision@1: 80% · Precision@3: 100% · SBERT + FAISS + Qwen2.5-1.5B
🔗 Live Demo
SignStream — ASL-to-speech pipeline (video → sign → English → audio)
Efficient pose-based Transformer, fine-tuned T5 for gloss-to-text.
74.70% val / 67.40% test top-1 · 18.65M params · 2,731 classes · ASL Citizen (~83K videos)
Diabetic Retinopathy Grading — Ordinal severity classification
EfficientNetB3 + CORAL ordinal regression, deployed as clean inference package.
QWK 0.9143 · 81.86% accuracy · weighted F1 0.824 · APTOS 2019
Building GenAI systems and writing the AI-grad → AI-Engineer roadmap for Arabic-speaking AI graduates.