I’m an AI Engineer focused on building production-ready RAG and LLM applications with strong backend foundations.
My work combines:
- AI backend engineering
- FastAPI services, async APIs, Dockerized deployment, and maintainable system design
- RAG & LLM applications
- multilingual document chat, retrieval pipelines, prompt orchestration, and source-grounded answers
- Model alignment & safety
- RLHF-style review, adversarial testing, output quality analysis, and guardrail-oriented thinking
- Building multilingual RAG systems and agentic AI workflows
- Improving LLM reliability, retrieval quality, and explainability
- Exploring production-grade backend patterns for AI products
- AI Backend Engineer at Springer Capital
- AI Model Alignment Specialist (RLHF) at Outlier
- AI Video Data Specialist & Quality Auditor (Tier 3) at Atlas Capture
- B.Sc. in Computer Science — Mansoura University
- Based in Gharbia, Egypt | Open to Relocate
- Built an end-to-end multilingual RAG application using FastAPI, Next.js, Groq, and FAISS
- Supports Arabic/English PDF chat, agentic routing, source citations, and retrieval transparency
- Designed to showcase practical AI engineering around retrieval, routing, backend architecture, and explainability
- Built a production-style FastAPI service for fraud prediction
- Included preprocessing, model inference, Dockerized deployment, and API documentation
- Focused on practical ML system design and backend delivery
- AI Backend Engineering
- Building scalable APIs and backend services for AI-powered products
- RAG Engineering
- Designing retrieval pipelines, document-grounded answers, and multilingual AI workflows
- AI Safety & Alignment
- Experience in RLHF-style evaluation, red teaming, and output quality analysis
- Production Mindset
- Focus on Docker, maintainability, reliability, and real deployment considerations
- AI Engineer
- AI Backend Engineer
- LLM / RAG Engineer
- Applied AI Engineer
I’m especially interested in teams building intelligent products, backend-heavy AI systems, and production-ready LLM applications.