Imane.BENZEGUNINE
EXPERIENCE

Learning through building.

Data engineering, analytical systems, and applied AI in professional settings.

01

March – August 2026

Data Engineer AI (Internship)

Inetum Casablanca

  • Designed a Medallion Architecture (Bronze/Silver/Gold) on Microsoft Fabric to industrialize ServiceNow data processing: ingestion into Lakehouse/OneLake, PySpark/Python transformations, and quality controls across ~40 business variables.
  • Designed a star schema and developed data pipelines as well as Power BI/DAX dashboards, including SLA calculations, anomaly detection, and automated alerts via Microsoft Teams.
  • Developed a RAG platform for structured and unstructured data, integrating ingestion, cleaning, chunking, hybrid FAISS/BM25 search, and language models; deployed using Docker and AWS EC2.

Technologies: Python, Microsoft Fabric, SQL, Airflow, PostgreSQL, AWS Ec2, Docker, Lakehouse

ServiceNow Incident AnalyticsChronoBrain — RAG Platform
02

July – Sept 2025

Data Engineer (Internship)

Akkan Crowdfunding Casablanca

  • Deployed a Big Data infrastructure consolidating funding data from more than 10 simultaneous clients.
  • Implemented an ETL pipeline feeding an analytical Data Warehouse for decision-making purposes.
  • Designed a multi-tenant architecture providing each client with dedicated data warehouses and customized dashboards.

Technologies: Python, Apache Spark, Airflow, SQL Server, ClickHouse, Power BI, Azure VM

Multi-tenant Data Warehouse & ETL Pipeline
03

July – Aug 2024

BI Engineer (Internship)

Everest Indus Remote

  • Developed pipelines for extracting, transforming, and cleaning raw data for Power BI.
  • Modeled data structures using star schema to monitor more than 5 critical performance indicators.
  • Created interactive dashboards with DAX measures to help management interpret data and make decisions.

Technologies: Power BI, Data Modeling, DAX

Power BI Pipelines & KPI Dashboards
04

Juil – Sept 2024

Data Engineer - Pipeline ML (Stage)

3D Smart Factory À distance

  • Conception d’un pipeline de bout en bout pour l’ingestion, le traitement et la préparation de données d’images.
  • Application de techniques d’augmentation de données afin d’enrichir et de renforcer les jeux de données d’entraînement.
  • Entraînement et évaluation de modèles prédictifs (CNN) atteignant une précision de 92 % en classification d’images.

Technologies : CNN, TensorFlow, PyTorch, Keras, Data Augmentation

Pipeline de données d’images & classification CNN
THE NEXT CONVERSATION

Good work starts
with a conversation.

Let’s talk

Have a role in mind, or a data challenge to work through?