Computer Vision and Geospatial Data Science
Work description
The work and training plan focuses on the data pipeline, ETL, and MLOps needed to support the DFence project, specifically in extracting information from satellite images and sensors (IoT/UAV), and characterising soils and animals to feed the system's models and dashboards. Tasks: - Contribute to the state of the art and support the writing of technical and scientific documentation (data procedures and guides). - Design and implement ETL pipelines for satellite images (e.g., Sentinel), UAVs, and IoT sensors, with quality control and cataloguing/metadata. - Maintain data infrastructure (data lake/warehouse), dataset versioning, and access/serving APIs. - Develop computer vision pipelines for soil and animal characterisation (pre-processing, indices/NDVI, segmentation/detection, feature extraction). - Implement MLOps (reproducible training/validation, experiment tracking, CI/CD, containerisation and deployment). - Create analytical scripts and dashboards for data/model monitoring and prototype testing support, ensuring good GDPR practices.
Academic Qualifications
- Master's degree in Computer Engineering/Computing, Data Science or related fields.
Minimum profile required
- Average grade in bachelor's and master's degrees above 14.- 1 article accepted for presentation at a conference or publication in a journal.
Preference factors
- Fluency in Portuguese. - Candidate enrolled in or attending a doctoral programme. - Experience in data engineering/ETL, MLOps and geospatial computer vision (Python, GDAL/rasterio, GeoPandas, PyTorch/TensorFlow). - Knowledge of IoT/APIs, SQL/NoSQL and geospatial data management.
Application Period
Since 27 Nov 2025 to 12 Dec 2025
Centre
Enterprise Systems Engineering