Description

I am a Data Scientist and Data Engineer specializing in end-to-end data solutions, with a strong focus on R programming, automated data pipelines, and multi-source data integration.

I help organizations transform complex and fragmented data into reliable, structured, and analysis-ready systems, covering the full data lifecycle: ingestion, cleaning, reconciliation, transformation, and delivery of actionable insights.

My expertise combines R-based analytics (tidyverse, statistical workflows, reproducible reporting with Quarto) with modern data engineering practices, including workflow automation, containerization with Docker, and CI/CD principles for reproducible and scalable data systems.

I have worked across multiple domains such as healthcare, investment, e-commerce, and research environments, designing robust solutions for data reconciliation, integration, and automation of analytical workflows.

My approach is both technical and practical: building clean, maintainable, and reproducible data systems that support better decision-making.

Areas of expertise:

Data Engineering (ETL pipelines, data integration, data transformation)
R Programming (tidyverse, statistical analysis, automation)
Multi-source Data Integration & Reconciliation
Reproducible Reporting with Quarto (data-driven documents, reporting/research workflows)
Workflow Automation & Data Processing Systems
Dockerized Data Applications & Reproducible Environments
CI/CD concepts applied to data pipelines and analytics workflows
Data Cleaning & Structuring of complex heterogeneous datasets
Analytics & Decision Support Systems
Cross-domain experience (Medicine, Finance, E-commerce, Research data)

Langues

Arabe
Bilingue ou natif
Anglais
Capacité professionnelle complète
Français
Capacité professionnelle complète

Préférences en matière de lieu de travail

En télétravail uniquement

Travaille majoritairement à distance

Independent Data Scientist & Data Engineer
INDEPENDENT DATA CONSULTANT, PARTTIME INSTRUCTOR, RESEARCHER
HIGH TECH
septembre 2024 - Aujourd'hui (1 an et 9 mois)
Tunis, Tunisie
• Provide R consulting and data management services, including data cleaning, reconciliation, and integration across multiple heterogeneous sources (APIs, databases, files), ensuring high-quality and consistent datasets for analysis.

• Design and deliver reproducible analytical workflows using R and Quarto, enabling transparent, validated, and scalable data analysis pipelines across different domains such as investment and e-commerce.

• Support organizations and researchers in improving data-driven decision-making by streamlining data workflows, automating processing steps, and enhancing analytical efficiency through robust R-based solutions and best practices.
R programming Data visualisation Data Engineering Quarto RStudio
Synodis
PRINCIPAL DATA SCIENTIST
SECTEUR MÉDICAL
juin 2017 - mai 2024 (6 ans et 11 mois)
Tunis, Tunisie
• Designed and implemented end-to-end data pipelines (ETL) for integrating, cleaning, and structuring complex datasets from multiple heterogeneous sources, ensuring data consistency and reliability across systems.

• Built automation frameworks and data workflows for large-scale data migration, including patient data processing across 65 clinical establishments with strict accuracy and completeness constraints.

• Developed data integration and reconciliation systems for linking multi-source entities (e.g., doctor–researcher profiles), enabling accurate computation of research-based compensation models.

• Collaborated with cross-functional teams to design and optimize data migration strategies, aligning technical workflows with domain-specific business and data requirements.

• Engineered scalable workflows for processing and consolidating data from 15+ disparate systems, supporting practitioners across clinical establishments.

• Processed and structured scientific publication data (PubMed) to enrich research profiles and enhance data-driven content for external platforms.

• Developed and maintained R Shiny applications and dashboards for data analysis, document processing, and interactive reporting.

• Deployed production-grade analytical applications using Docker, ShinyProxy, and Azure cloud infrastructure, ensuring scalability and reproducibility.

• Contributed to machine learning models for predicting medical procedures from electronic health records (EHR).

• Researched and implemented NLP techniques for document preprocessing and information extraction in R&D environments.

• Collaborated with DevOps, support, and testing teams, improving automation pipelines using tools such as Robot Framework and CI/CD practices.
ETL/ELT DevOps R programming Git RShiny
R-HTA in LMICs
Scientific Committee Member
SECTEUR MÉDICAL
novembre 2024 - Aujourd'hui (1 an et 7 mois)
Tunis, Tunisie
• Contributed to Health Technology Assessment (HTA) workshops and initiatives, using R-based approaches to support data-driven learning and capacity building in underserved regions.

• Supported cross-team collaboration and coordination, helping streamline communication and improve execution of committee activities.

• Assisted in the preparation and delivery of workshop content and training sessions, focusing on practical applications of R for data analysis and research workflows.

• Contributed to the development and maintenance of internal digital knowledge resources and communication materials, improving accessibility and engagement within the organization.
R programming Data science Research HTA Quarto