Remote Sensing Analyst

Job Title: Remote Sensing Analyst Overview We are seeking a motivated Remote Sensing Analyst with a strong academic foundation in hyperspectral and multispectral remote sensing, as well as SAR analysis. The ideal candidate is a recent Master's graduate who will support the execution of end-to-end workflows for crop monitoring, land‑cover change detection, and applied research. You will write reproducible Python code, analyze geospatial datasets, and collaborate with our team to translate scientific outputs into actionable insights. Key Responsibilities Support the design and implementation of remote sensing workflows, including data discovery, pre-processing, atmospheric correction, georeferencing, co-registration, mosaicking, and feature extraction. Develop and maintain reproducible Python code and scripts (utilizing GDAL, rasterio, xarray, numpy, pandas) for satellite data ingestion, preprocessing, and analysis. Work with hyperspectral datasets (e.g., AVIRIS, Hyperion, PRISMA, EnMAP) to perform spectral feature extraction, dimensionality reduction, continuum removal, spectral unmixing, and classification. Analyze multispectral and SAR datasets (Sentinel-2, Landsat, Sentinel-1) for calculating vegetation indices, biomass estimation, water stress detection, and crop-type mapping. Assist in creating time-series workflows for land cover change detection, phenology analysis, and anomaly detection using change detection algorithms and time-series models. Build and validate classification and regression models (machine learning) for crop identification, yield estimation, and stress detection, while performing cross‑validation and error analysis. Implement data quality assurance and validation strategies using field data. Produce clear technical reports, visualizations, and maps for stakeholders and clients. Required Qualifications and Experience Master’s degree in Remote Sensing, Geospatial Science, Earth Observation, Environmental Science, GIScience, or a closely related field. Recent graduate or up to 2 years of professional/academic experience in remote sensing and geospatial analysis, with demonstrable project work handling hyperspectral data and SAR. Proficient Python skills and practical experience with geospatial libraries: GDAL/OGR, rasterio, geopandas, xarray, rioxarray, shapely, pyproj. Academic or practical experience with hyperspectral data workflows, including reading ENVI/BSQ formats, utilizing spectral libraries, and applying dimensionality reduction (PCA/ICA) or classification techniques (SAM, SVM). Understanding of SAR processing concepts and tools, specifically utilizing Sentinel-1 data and speckle filtering. Experience working with time-series analysis frameworks for Earth Observation data using Python. Strong background in machine learning applications for remote sensing (e.g., scikit-learn). Proven ability to produce clear visualizations and maps (Matplotlib, Seaborn, Folium, Kepler.gl, QGIS/ArcGIS). Strong written and verbal communication skills; ability to present technical work clearly. Preferred Skills Experience with hyperspectral sensors beyond standard research datasets (PRISMA, EnMAP) or commercial VNIR/SWIR sensors. Knowledge of advanced SAR techniques: polarimetry, interferometric analysis (InSAR), and coherence time-series. Fieldwork experience in agricultural contexts and familiarity with crop phenology and agronomy. Deliverables and Success Metrics Reproducible scripts and documented pipelines to convert raw satellite data into analysis-ready datasets. Validated crop-type maps with accuracy reporting and error analysis. Technical reports, visualizations, or client-ready deliverables delivered on schedule.