AI Engineer
aka Romia
I build multi-agent LLM systems. At Zaylon AI, the company I co-founded, the agents I built let customers shop and check out by chatting on WhatsApp and Instagram in their own dialect.
Zaylon AI
Conversational commerce for MENA merchants, on WhatsApp and Instagram
Zaylon turns WhatsApp and Instagram into full sales channels for MENA merchants. Customers browse, ask in their own dialect, and check out without ever leaving the chat. It reads Egyptian Arabic and Franco-Arabic the way a local would, matches a product from a photo, recovers carts on its own, and carries someone from the first question to a paid order. We built the dialect engine and the conversational commerce layer in-house.
0
Platforms
0
Channels
0
Payments
0
Dialects
What it does
Handles the whole conversation end to end: answers product questions, builds the cart, and closes the order, all inside the same chat and without a human stepping in.
DialectBridge detects whether a customer is writing English, Egyptian Arabic, or Franco-Arabic and answers back in the same dialect.
Customers can send a photo of a product, and Zaylon matches it against the merchant's catalog.
Catalog and orders stay in sync across Shopify, Salla, WooCommerce, Odoo, YouCan, and Zoho.
Follows up on abandoned carts and steps in when a conversation starts to turn negative.
Takes payments through Stripe, Paymob, and Fawry, with every charge confirmed by a verified webhook.
A merchant dashboard with a live inbox, analytics, RFM segmentation, and A/B testing.
Each merchant's data is encrypted on its own and isolated at the row level, so tenants never see each other.
Integrations built
Connected to the platforms MENA merchants already use
Messaging
E-Commerce
Payments
Shipping
Built with
Projects
8 projects
Zaylon AI
An AI that sells over WhatsApp and Instagram for MENA merchants, carrying a customer from the first product question to a confirmed payment, all inside the chat.
View Case StudyA worked example of production RAG that runs on CPU: dense and lexical retrieval fused with reciprocal rank fusion, cross-encoder reranking, grounded citations, and an evaluation harness that measures the difference.
An event-driven banking system: five Spring Boot services behind a gateway, with a transfer saga over Kafka that is provably correct under concurrency, retries, and restarts.
Read the write-upSpeaker-independent speech emotion recognition on RAVDESS, rebuilt to remove a speaker-leakage flaw that inflates most published results. WavLM-large audio with learnable layer-weighting, fused with a facial-expression model.
An engine that measures the fingerprint of how you write from your own samples, then adapts your own drafts toward that voice. Interpretable stylometric features paired with a StyleDistance neural style embedding and an in-context rewrite.
Talos
Graduation project (team): a multi-user RAG platform for chatting with your own uploaded documents, with answers streamed back and cited inline. I owned the ingestion and retrieval core.
Connect4 AI Agent
A Connect 4 agent that searches the game tree with minimax and alpha-beta pruning.
CSP Sudoku Solver
Constraint satisfaction solver using backtracking, AC-3 arc consistency, and MRV heuristic for efficient puzzle solving.
Experience
Software Engineer & Co-Founder
Co-founded Zaylon and built its AI system and backend: a LangGraph tool-calling agent and tri-lingual NLP on a FastAPI backend with PostgreSQL/Redis, multi-tenant isolation, and Docker deployment, serving MENA merchants across WhatsApp, Instagram, and web.
- ▸Built the conversational AI in LangGraph as a single tool-calling agent with about 30 scoped tools across sales, support, and checkout, consolidated from an earlier multi-agent supervisor for reliability and easier reasoning
- ▸Built DialectBridge, an NLP pipeline that detects whether a customer is writing English, Egyptian Arabic, or Franco-Arabic and answers in the same dialect
- ▸Built hybrid product search combining keyword matching, semantic vector similarity, and Reciprocal Rank Fusion scoring
- ▸Wrote the FastAPI Python backend and its service architecture, containerized with Docker for deployment
- ▸Built multi-tenant security: argon2id key auth, per-merchant row-level isolation across roughly 80 tables, and semgrep CI gates enforcing tenant scoping
- ▸Built a Postgres-backed saga engine with reverse-order compensation so a failed checkout step rolls back cleanly
- ▸Batched rapid-fire WhatsApp messages in Redis into a single turn before invoking the agent, so it reads the whole thought at once instead of replying to each fragment
Software Integration Engineering Intern
Ejada
Worked on core banking integration systems, building APIs and event-driven messaging pipelines.
- ▸Built RESTful API endpoints for core banking operations using Spring Boot with query optimization and Redis caching for frequently accessed account data
- ▸Configured Apache Kafka producers and consumers for asynchronous transaction processing, decoupling payment events from the main request lifecycle
- ▸Implemented API gateway security with OAuth2 authentication, rate limiting, and request validation using WSO2 API Manager
AI Coding Expert
Freelance · Independent Contractor
Evaluated and improved LLM-generated code across multiple platforms, contributing to RLHF training data for frontier AI models.
- ▸Evaluated LLM-generated coding solutions across Python, backend systems, and algorithmic problems for RLHF data pipelines used to train frontier AI models
- ▸Developed quality rubrics and prompting strategies for code generation, measuring correctness, efficiency, style adherence, and edge case handling
- ▸Reviewed and ranked thousands of code samples, providing detailed feedback on reasoning chains, code structure, and technical accuracy
Automotive Cybersecurity Intern
Swift-ACT
Contributed to automotive cybersecurity research, building security scenario catalogs and running attack simulations in vehicle simulation environments.
- ▸Built security scenario catalogs with threat models, attack vectors, and mitigations for CAN bus and ECU communication systems following automotive cybersecurity standards
- ▸Designed and ran cybersecurity test scenarios in Dyna4 and CARLA, covering spoofing, replay, and denial-of-service attacks on vehicle CAN networks
- ▸Used Vector CANoe for CAN bus simulation and analysis, monitoring message traffic, injecting fault conditions, and validating ECU response behavior under adversarial inputs
- ▸Conducted fuzz testing on Automotive Emergency Braking (AEB) components, identifying edge cases in sensor fusion timing and brake actuation logic under corrupted input data
Tech Stack
Backend
Powers Zaylon AI, Virtual Banking, ContextIQ RAG
AI / ML
Powers Zaylon AI, ContextIQ RAG, Emotion Recognition
DevOps & Cloud
CI/CD and deployment across all projects
Languages
Primary: Python, Java. Growing: Go, TypeScript
About Romia
I co-founded Zaylon AI and built its AI system and backend: the LangGraph agent that sells over WhatsApp and Instagram, the tri-lingual NLP, and the FastAPI backend behind them. I work across the stack but lean toward backend and AI. B.Sc. in Computer and Communications Engineering with an AI concentration from Alexandria University. I speak English, Arabic, German, and Spanish, and I play guitar.
Education
B.Sc. in Computer and Communications Engineering, AI concentration
Alexandria University, Faculty of Engineering
GPA: 3.73 / 4.0
Spoken Languages
Certifications
micro1 Certified Software Engineer
micro1 · 2026
Google AI Agents Intensive
Google / Kaggle · 2025
Meta Back-end Developer Specialization
Coursera
AWS Cloud & ML Foundations
AWS Academy
Competitions & Hackathons
Let's Connect
I like building systems that actually ship. If you're working on agents, backend infrastructure, or AI products, or hiring for one, say hi.