Beirut, Lebanon · Open to opportunities
I build AI systems, data platforms, and search infrastructure for institutions that shape policy.
About
Data Engineer and Machine Learning Specialist with 5+ years of experience designing, building, and maintaining data pipelines, metadata systems, search platforms, and AI-driven applications for large-scale institutional environments. At the United Nations ESCWA, I ship LLM-powered products — multi-agent report generators, RAG policy advisors, and semantic search — that turn sprawling document repositories into evidence for policymaking.
Education B.E. Civil & Environmental Engineering, Beirut Arab University (2015 — 2020). Honor student — CGPA 3.84 / 4. First place, 2017 LIRA Competition (3D concrete printing).
From multi-agent report generators to RAG advisors used inside government portals — I build LLM systems that make it to production, not just to demos.
Five years of pipelines: ingestion, validation, metadata, lineage. Spark, Airflow, Delta Lake, and Azure — organized so analysts and models can rely on it.
My work powers policymaking tools across the Arab region — search for development portals, simulators for policymakers, forecasts for economists.
Selected work
Multi-agent LLM report generation
Co-developed a multi-agent LLM system that produces high-quality reports and documents on demand by retrieving and synthesizing content from Manara’s document repository — orchestrated agents for research, drafting, and quality control.
ESCWA’s first LLM policy advisor
Built ESCWA’s first LLM-powered RAG policy advisory assistant over Manara’s document repository, delivering accurate, context-aware answers. Deployed as a standalone web app and integrated into the Manara and Arab Development Portal Data Catalog.
RAG analytics for Qatar’s Ministry of Labour
Developed an LLM-powered RAG chatbot leveraging government employment data to deliver analytical insights that support evidence-based policymaking for Qatar’s Ministry of Labour.
Embedding pipelines + Azure AI Search
Designed and built the search functionality for the Manara and Arab Development Portal: pipelines that embed dataset and document metadata, ingest into Azure AI Search, and serve an optimized retrieval process. Also built LLM pipelines for metadata generation and document classification.
Optimization models for policymakers
Built the core engine powering optimization models that simulate index and indicator values for the Index Simulator for Policymakers in the Arab Region — plus contributions to the Financing for Development and Multidimensional Poverty Index optimization models.
Deep learning for macro forecasting
Led the data science team in assessing the feasibility of a GDP forecasting model targeting 3% accuracy, using deep neural networks and ensemble machine learning techniques.
Python app replacing manual reporting
Built a Python web application that ingests geotechnical data from Excel, runs automated analysis and visualization, and compiles downloadable reports — dramatically reducing manual effort at Dar Al Handasah.
Experience
Mar 2023 — Jun 2026
United Nations ESCWA — ICT Section · Beirut, Lebanon
Aug 2021 — Mar 2023
United Nations ESCWA — ICT Section · Beirut, Lebanon
Nov 2020 — Aug 2021
United Nations ESCWA · Beirut, Lebanon
Mar 2024 — Aug 2024
Terascom · Beirut, Lebanon
Jun 2022 — Jun 2023
Dar Al Handasah (Shair) · Beirut, Lebanon
Capabilities
Contact
I'm open to roles and collaborations in machine learning, data engineering, and AI products. The fastest way to reach me is email.