Open to opportunities

Youssef Maghraoui

@youssefmaghraoui

Message

Data & AI Engineer building end-to-end data pipelines, cloud warehouses, and LLM-powered systems.

Tunisia

Message

What I'm looking for

I’m looking for a fast-moving team where I can own end-to-end data pipeline delivery—cloud warehouses, ETL/ELT, and production-ready LLM/RAG systems—while working effectively async across time zones.

I’m a Data & AI Engineer focused on shipping end-to-end data pipelines, cloud warehouses, and LLM-powered solutions. In my capstone internship, I migrated a full data stack from DOMO to BigQuery, redesigned data models, and rewrote pipelines to reduce processing latency while improving query performance.

I also build reliable ingestion and analytics experiences—scheduled ETL pipelines for operational data and Evidence.dev dashboards with clean datasets and metric validation. Previously, as a Software Engineer Intern, I delivered a real-time NLP + semantic search + web scraping pipeline, cut processing time from minutes to seconds, and implemented an end-to-end graph-based RAG system with entity-mapping validation. I bring a strong async, cross-time-zone working style and a practical mindset shaped by ETL/ELT, Python/SQL, and LLM frameworks.

Experience

Work history, roles, and key accomplishments

Current

Data Engineer Intern

Current

Hivenet

Jan 2025 - Present (1 year 4 months)

Migrated the data stack from DOMO to BigQuery by designing new data models and rewriting pipelines to reduce processing latency and improve query performance. Built scheduled ETL pipelines for reliable warehouse ingestion/transform/load and developed Evidence.dev dashboards; capstone built Waggle, an LLM-powered AI data analyst connecting to multiple databases and generating SQL-driven artifacts v

BigQuery ETL Data Modeling SQL Orchestration Dashboarding

Software Engineer Intern

Value - VigilantX

Jan 2024 - Present (2 years 4 months)

Built and maintained a real-time data processing pipeline spanning NLP, semantic search, and web scraping, and added regression tests that reduced average processing time from minutes to seconds. Designed a document ingestion framework with automated quality checks and implemented a graph-based RAG system with entity-mapping validation and context-aware scoring.

Python NLP Semantic Search Web Scraping Regression Testing Data Pipelines RAG Context Aware Scoring

Data Science Engineer

SellMax

Jan 2023 - Present (3 years 4 months)

Analyzed and validated customer behavior data using Python and SQL, cross-checking predictive model outputs to ensure data integrity. Built interactive Tableau dashboards by iterating on business requirements and validating that displayed metrics matched underlying data sources.

Python SQL Data Validation predictive modeling Tableau Data Integrity Analytics Metrics

Education

Degrees, certifications, and relevant coursework

ESPRIT School of Engineering

Engineering Degree in Data Science, Data Science

2021 - 2026

Grade: Dean's List (2022–2024)

Activities and societies: Academic Excellence Scholarship; Co-Founder & Technical Committee, Securinets (Esprit branch).

Pursuing an Engineering Degree in Data Science at ESPRIT School of Engineering. Earned Dean's List honors (2022–2024) and received an Academic Excellence Scholarship.