Spatial Data Engineer (GIS)

Job Responsibilities Participate in the acquisition, assessment, and organization of spatial data: Digital Elevation Models (DEMs), orthophotos, vector data (administrative boundaries, roads, water bodies, building footprints, POIs), oblique photogrammetry models, and LiDAR point clouds—including sourcing public datasets and verifying client-provided data; Participate in data cleaning and repair: filling missing areas, edge matching, outlier and noise correction, topological error fixing, attribute field standardization, projection transformation, and coordinate system unification—transforming real-world data (which almost always has quality issues) into usable datasets is the core value of this role; Participate in processing oblique photogrammetry models and point cloud data: format conversion, coordinate correction, object-level modeling (singleization), tiling reorganization, thinning, and classification—resolving common issues such as floating models, streaking artifacts, and voids; Automate repetitive data processing tasks through scripting, and contribute to building reusable workflows and quality assurance scripts—ensuring clear, objective criteria for data usability rather than relying on subjective judgment; Participate in exploring AI-based methods for spatial data processing: point cloud semantic segmentation, automatic feature extraction, change detection in imagery, and large language model–assisted parsing and anomaly detection of unfamiliar data formats. Qualifications Bachelor’s degree or higher (expected graduation in 2027) from a top-tier university (C9 League or Double First-Class institutions) in Geographic Information Science, Surveying and Mapping Engineering, Remote Sensing Science and Technology, Photogrammetry, Cartography and Geographic Information Systems, or related fields—Master’s degree preferred; Proficiency in Python for independent development of data processing scripts—this is a mandatory requirement, as the role heavily relies on script-based batch processing rather than GUI point-and-click operations; Solid understanding of fundamental spatial data processing principles: coordinate systems and map projections (CGCS2000, WGS84, Web Mercator, Gauss-Kruger zone-based systems), vector and raster data structures, topological relationships, and the appropriate use cases for 7-parameter vs. 4-parameter coordinate transformations; Hands-on experience using ArcGIS or QGIS for actual data processing tasks, with familiarity in GDAL/OGR basic usage; Demonstrated project experience—course projects, research topics, competition entries, or internship work—all acceptable, provided you can clearly articulate data sources, processing methodology, and quality-related challenges encountered; Regular use of AI-assisted programming tools, with the ability to explain how you leverage them to decode unfamiliar data formats and cross-validate outputs—critical in GIS, where AI tools often produce plausible but incorrect answers regarding formats and coordinates; Strong data quality awareness: ability to proactively assess data correctness before proceeding, rather than proceeding blindly. Preferred Qualifications (Bonus Points) Familiarity with Python’s spatial data ecosystem (GeoPandas, Rasterio, Shapely, PyProj, laspy, etc.); Experience with photogrammetry software (e.g., ContextCapture, Metashape, DJI Terra), including understanding of processing workflows and key parameters; Knowledge of 3D Tiles, OGC service standards (WMS/WMTS/WFS), or spatial databases (e.g., PostGIS); Prior academic or competition experience in point cloud deep learning, remote sensing image intelligent interpretation, or automated feature extraction; Recognition in GIS/surveying-related academic competitions, published papers, or publicly available data processing tools on GitHub.