Description

Looking to make sense of your data, automate your workflows, or predict what’s coming next? That’s exactly what I do.

I help companies transform raw data into business value by designing real-time pipelines, dashboards, and intelligent models that don’t just process information, but deliver insights you can act on.

✅ What makes me different:

I combine Data Engineering (Kafka, Spark, Airflow, AWS) with Data Science (ML, NLP, Deep Learning) → meaning I don’t just move data, I also make it smarter.

I’ve built a real-time monitoring system for Orange that reduced anomaly detection time by 70%.

I created a full-stack shipment management app with Flask & APIs that handles everything from tracking to automatic PDF/email generation.

📦 Projects I can deliver for you:

End-to-end ETL & ELT pipelines (real-time & batch).

Monitoring platforms & dashboards (Metabase, Power BI, custom solutions).

Predictive models: anomaly detection, recommendations, forecasting.

Custom APIs & web apps to make your data accessible and useful.

If you need someone tech-savvy, reliable, and results-driven, I’ll make sure your project not only works, but creates real impact 🚀.

Languages

French
Native or bilingual
English
Conversational
Arabic
Native or bilingual

Workplace preferences

Remote only

Primarily works remotely

Sofrecom Tunisie
Data Engineering Intern
April 2024 - September 2024 (5 months)
• Designed and implemented a real-time monitoring pipeline using Kafka, Spark Streaming and MongoDB to track CPU usage and query execution. → Reduced performance anomaly detection time by 70%.
• Developed batch pipelines with Spark SQL to compute weekly metrics (query counts, data volumes, execution times).
• Built and deployed a Metabase dashboard for KPI visualization, enabling proactive monitoring of the Stargate platform.
• Developed a prediction model for query volume estimation.
• Automated batch jobs orchestration using Apache Airflow.
• Deployed services via Docker Compose and GitLab CI/CD.
Python Apache Kafka Apache Spark DevOps Machine learning
Banque de l'Habitat (BH)
Data Analyst Intern
June 2023 - August 2023 (2 months)
• Collected, cleaned, and transformed customer data from Oracle and MySQL databases.
• Built a customer segmentation model (K-means) and a predictive model (LSTM) for spending behavior.
• Designed and populated a Data Warehouse using SQL Server and SSIS.
• Created Power BI dashboards for purchasing behavior and income visualization.
KODY
Software Developer Intern
June 2022 - September 2022 (3 months)
• Developed a class diagram serialization system.
• Wrote user documentation and internal guides for development teams.