Data Analyst-Remote Sensing

Role Overview

As a Remote Sensing Data Analyst at Pula, you will process satellite, field, and other geospatial data to assess crop conditions, estimate yields, and inform agricultural insurance and field activities. Working with the Associate Manager and field and data-collection teams, you will check analytical results against on-the-ground evidence and help strengthen the methods and procedures used across projects.

Key Responsibilities

• Source and analyze satellite imagery and related datasets, including vegetation indices, rainfall, and soil moisture, using data from platforms such as Sentinel, Landsat, MODIS, and Planet.
• Build and maintain geospatial workflows for crop mapping, crop monitoring, yield estimation, and loss assessment.
• Compare remote sensing results with crop-cutting experiment findings and survey data; investigate discrepancies and document validation results.
• Manage and analyze field boundaries, GPS locations, and administrative data in GIS software, and contribute to spatial sampling plans for field research.
• Check the quality of geospatial and field-collected data against standard procedures, identify weaknesses in those checks, and recommend improvements.
• Set up surveys and assign field agents through the internal data-collection platform, and support survey design and fieldwork when needed.
• Prepare analysis, maps, reports, and practical recommendations; identify project risks and suggest appropriate methods for analysis and operational review.
• Develop and assess improved workflows, write technical guidance and training materials, support field staff in adopting new procedures, and provide regular updates to the manager.

Requirements & Qualifications

• Bachelor’s degree in Statistics, Economics, Agricultural Economics, Agribusiness Management, Geography or Geoinformatics, Environmental Science, Information Systems, or a related discipline.
• At least two years of data analysis experience; experience in an NGO or agri-tech setting is an advantage.
• Practical experience handling satellite imagery or geospatial datasets.
• Proficiency in Python and R, including relevant geospatial tools such as rasterio, geopandas, GDAL, sf, or terra.
• Working knowledge of QGIS or ArcGIS and cloud-based geospatial analysis platforms such as Google Earth Engine.
• SQL proficiency and experience creating visualizations in Power BI or a comparable tool.
• Familiarity with mobile survey platforms such as CommCare, KoboToolbox, or SurveyCTO.
• Understanding of statistical approaches to validation, sampling, and model assessment; machine-learning experience in classification or regression is beneficial.
• Clear written and verbal communication, including the ability to present technical findings through concise reports, maps, and presentations.
• Ability to collaborate effectively, work independently, balance competing priorities, and deliver to deadlines.
• Experience with agricultural insurance, index-based products, smallholder farming, SAR or weather data, or cloud-based geospatial pipelines is an advantage.