Abdelrahman Abouroumia

Software Engineer & Co-Founder

Zaylon AI

May 2025 – PresentCurrent

Co-founded and built the full-stack platform: Next.js merchant dashboard, FastAPI backend with PostgreSQL/Redis, Docker deployment, and multi-agent AI system serving MENA merchants across WhatsApp, Instagram, and web.

• ▸Built full-stack platform: Next.js/React merchant dashboard with real-time inbox, analytics, and A/B testing on top of a FastAPI Python backend with Docker containerized deployment
• ▸Integrated 6 e-commerce platforms (Shopify, Salla, WooCommerce, Odoo, YouCan, Zoho) via REST APIs with webhook-driven sync, idempotent operations, and retry logic
• ▸Architected a multi-agent LangGraph system with a supervisor routing conversations to 3 specialized agents (Sales, Support, Checkout), each with scoped access to a subset of 10 AI tools
• ▸Engineered DialectBridge, a tri-lingual NLP pipeline that auto-detects whether a customer is writing in English, Egyptian Arabic, or Franco-Arabic and matches the response dialect accordingly
• ▸Built hybrid product search combining keyword matching, semantic vector similarity, and Reciprocal Rank Fusion scoring, deployed across WhatsApp and Instagram channels
• ▸Designed Redis message accumulation to batch rapid-fire WhatsApp messages into a single coherent turn before invoking the agent, reducing token waste and fragmented responses
• ▸Built multi-tenant architecture with per-merchant encryption, row-level data isolation, and webhook-verified payment processing through Stripe, Paymob, and Fawry

Software Integration Engineering Intern

Ejada

Jul 2025

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

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

Aug 2024 – Oct 2024

Contributed to automotive cybersecurity research, building security scenario catalogs and running attack simulations in vehicle simulation environments.

• ▸Built comprehensive security scenario catalogs documenting threat models, attack vectors, and mitigation strategies for CAN bus and ECU communication systems following automotive cybersecurity standards
• ▸Designed and executed cybersecurity test scenarios in Dyna4 and CARLA simulation environments, simulating real-world attack conditions on vehicle systems including spoofing, replay attacks, and denial-of-service on 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