Rabih Charaf Eddine

Data Specialist at Norna AI

Ensured data integrity by identifying and correcting pricing anomalies in large-scale e-commerce datasets using proprietary data visualization and validation tools; validated scraped product data and approved corrected records for production. Collaborated with the data scraping team to verify accuracy and completeness of extracted product data before ingestion; performed manual and semi-automated QA checks to validate pricing information, reducing downstream errors. Flagged recurring issues and worked with developers to improve scraping logic and data transformation workflows; gained hands-on experience in data validation, anomaly detection, and product lifecycle within an AI-driven retail analytics pipeline.

Data Analysis and IT Support Internship at United Nations ESCWA

Led data collection, cleansing, and analysis using Google Sheets and ASMES admin portal, producing actionable insights to optimize event planning. Maintained and supported the ASMES admin portal with HTML/JS, ensuring seamless functionality. Supported the Arab SMEs Summit by coordinating event logistics and managing stakeholder interactions. Proactively addressed technical issues to sustain portal performance and collaborated independently with multi-disciplinary teams in a fully remote setup.

Data Engineer Internship at MacroVision

Built an AI-powered chatbot integrating AI Agents, LLMs, and LangGraph, enabling semantic search of course content. Designed and deployed an ETL pipeline using AWS Lambda (TypeScript), SQS, and S3 to process video transcripts from the gold layer; generated embeddings with Amazon Titan via Bedrock and stored them in Pinecone VDB. Developed and containerized Lambda functions (Docker + ECR) with scalable IaC using Terraform. Integrated LangChain for orchestrating multi-step data processing workflows. Automated CI/CD with GitHub Actions and shell scripts for seamless deployment. Wrote unit and E2E automated tests with mocking for AWS services (e.g., S3, Bedrock, Pinecone). Managed secure operations via IAM , environment configs, and CloudWatch logging. Collaborated via GitHub by creating feature branches, opening PRs, addressing code reviews, and merging changes following best practices (squashing, rebasing).