10/08/2026 updated
100 % available
Data Scientist - Geospatial Analytics & Data Engineering
Forges, France
Worldwide
Master's in Data Science & Bioinformatics, University of Montpellier (2020-2022)Geographic Information SystemsApplication Programming Interfaces (APIs)Data AnalysisArcGIS (Software)ArcGIS ServersData ArchitectureData InfrastructureData IntegrationData MiningData ProfilingData SystemGeospatial IntelligenceGeoServerGeospatial AnalysisGEOS
Geospatial Analysis & Modelling
Expertise in geospatial analysis and connectivity modelling on raster and vector data using Python, GeoPandas, Rasterio, PostGIS, QGIS and ArcGIS. Development of country-scale spatial models and geospatial APIs for national connectivity studies covering large numbers of schools across multiple countries.
ETL Pipeline Development & Data Engineering
Design and deployment of automated ETL pipelines using Python, SQL, Azure Data Factory and AWS S3, including validation rules to improve data quality and traceability. Experience building and maintaining spatial databases and geospatial ETL workflows on Azure Databricks.
Data Visualisation & Reporting
Creation of decision-ready outputs including Power BI (DAX) and Spotfire dashboards, country reports and KPIs, giving operations and R&D teams visibility into performance and business metrics.
Machine Learning & Predictive Modelling
Building and evaluating predictive models in Python and R, including regression and classification approaches, applied to clinical data and geospatial scenarios.
Spatial Data Quality & Harmonisation
Validation and harmonisation of multi-source national datasets in collaboration with governments, regulators, Universal Service Funds and UNICEF across 20+ countries.
Cloud & DevOps
Working with Azure Databricks, Azure Data Factory, AWS S3, Git and Azure DevOps (CI/CD) to version and deploy analytical workflows and calculation engines at scale.
Bioinformatics & Statistical Analysis
Development of reproducible Python/R bioinformatics pipelines for microRNA evolutionary analysis and statistical analyses of clinical data across large patient cohorts.
Technical Documentation & Training
Delivery of technical presentations, hands-on workshops and user training for government, partner and operations teams, including international engagements in Maputo and Geneva.
Expertise in geospatial analysis and connectivity modelling on raster and vector data using Python, GeoPandas, Rasterio, PostGIS, QGIS and ArcGIS. Development of country-scale spatial models and geospatial APIs for national connectivity studies covering large numbers of schools across multiple countries.
ETL Pipeline Development & Data Engineering
Design and deployment of automated ETL pipelines using Python, SQL, Azure Data Factory and AWS S3, including validation rules to improve data quality and traceability. Experience building and maintaining spatial databases and geospatial ETL workflows on Azure Databricks.
Data Visualisation & Reporting
Creation of decision-ready outputs including Power BI (DAX) and Spotfire dashboards, country reports and KPIs, giving operations and R&D teams visibility into performance and business metrics.
Machine Learning & Predictive Modelling
Building and evaluating predictive models in Python and R, including regression and classification approaches, applied to clinical data and geospatial scenarios.
Spatial Data Quality & Harmonisation
Validation and harmonisation of multi-source national datasets in collaboration with governments, regulators, Universal Service Funds and UNICEF across 20+ countries.
Cloud & DevOps
Working with Azure Databricks, Azure Data Factory, AWS S3, Git and Azure DevOps (CI/CD) to version and deploy analytical workflows and calculation engines at scale.
Bioinformatics & Statistical Analysis
Development of reproducible Python/R bioinformatics pipelines for microRNA evolutionary analysis and statistical analyses of clinical data across large patient cohorts.
Technical Documentation & Training
Delivery of technical presentations, hands-on workshops and user training for government, partner and operations teams, including international engagements in Maputo and Geneva.
Languages
EnglishFluentFrenchFluentSpanishFluent
Project history
Development of geospatial models and analytical workflows in Python and PostGIS combining raster and vector data to assess connectivity gaps and evaluate deployment scenarios. Contribution to ITU's Connectivity Planning Platform (CPP), building geospatial APIs publishing results to GigaMaps, collecting and harmonising national datasets with governments and UNICEF across 20+ countries, and conducting 15 national-scale connectivity studies covering approximately 180,000 schools.
Design and deployment of 25+ automated ETL pipelines in Python, SQL and Azure Data Factory across Asia-Pacific laboratories. Delivery of 20+ Power BI and Spotfire dashboards for R&D and operations teams. Coordination of digital initiatives between technical teams in India and France, including user training and documentation.
Management and validation of clinical data for 10,000+ kidney transplant patients across 70+ variables. Building and evaluation of five predictive models in Python and R to support research on graft failure, with statistical analyses and communication of results to clinicians and researchers.