Senior GeoAI Engineer

The consultant will design, build and operationalize geospatial AI pipelines, models and services that turn Earth observation and other geospatial data into policy-relevant indicators and decision-support tools for Arab Member States. The work will be integrated into DSDS platforms and will strengthen ESCWA's in-house geospatial analytics capacity.

Hybrid

6 months

Background: The United Nations Economic and Social Commission for Western Asia (ESCWA) supports its 22 Arab Member States in achieving inclusive and sustainable development through evidence-based policymaking. Within ESCWA, the Decision Support and Data Science Division (DSDS) designs and operates AI platforms, data science tools, digital portals and decision-support systems. These include the Arab Development Portal (ADP), the ISPAR policy simulator, Polaris/Naseej (a multi-agent research and policy-synthesis engine), Mustashar (an Arabic-language AI legal advisory tool), and other specialized digital tools. Geospatial data and Earth observation are becoming central to policy analysis in the region. Satellite imagery, remote sensing, mobility data and other non-traditional sources can fill statistical gaps, produce near-real-time indicators, and support monitoring where conventional data are sparse, outdated or disrupted by conflict. Examples include tracking trade flows and border activity, measuring urban expansion and informal settlements, monitoring agricultural production and water use, assessing climate and disaster exposure, and estimating economic activity at the subnational level. DSDS is building a GeoAI capability to integrate geospatial intelligence into its platforms and analytical services. This work also supports the division's forthcoming practitioner manual, GeoInsights for Policymaking: Practitioner Manual for Geospatial Analysis and Decision Support, and related Development Account and technical cooperation work on AI, geospatial and non-traditional data. To lead the technical development of this capability, ESCWA seeks a Senior GeoAI Engineer. Duties and responsibilities: Under the overall supervision of the Chief of DSDS, the consultant will: a) GeoAI architecture and data infrastructure

• Design a scalable, cloud-based geospatial data architecture covering ingestion, storage, processing and serving of raster and vector data (e.g., Sentinel-1/2, Landsat, VIIRS night-time lights, commercial high-resolution imagery, OpenStreetMap, administrative boundaries).
• Establish reproducible pipelines using cloud-optimized formats (COG, GeoParquet, Zarr, STAC catalogues) and tools such as Google Earth Engine, Microsoft Planetary Computer or equivalent.
• Ensure interoperability with existing DSDS platforms (ADP, ISPAR, Polaris/Naseej) through APIs and standard data services (OGC-compliant where appropriate). b) Model development and use cases
• Develop, fine-tune and validate machine learning and deep learning models for priority use cases. Final selection will be agreed with the supervisor within the first month.
• Apply and adapt geospatial foundation models (e.g., Prithvi, SatMAE, Clay, SAM-based segmentation) where they add value over conventional approaches.
• Document model performance, uncertainty and limitations, including ground-truth validation against official statistics where available. c) Decision-support products
• Develop interactive geospatial dashboards and map-based decision-support tools for policymakers.
• Produce subnational indicator datasets that can feed into ISPAR simulations, ADP data products and Polaris/Naseej evidence synthesis.
• Explore integration of geospatial retrieval and analysis into LLM-based agentic workflows (e.g., natural-language querying of geospatial layers). d) Responsible AI and data governance
• Apply ESCWA's AI governance principles to all GeoAI work, including data provenance, privacy, bias assessment (e.g., urban/rural and regional representativeness), and the sensitivities of geospatial data in conflict-affected contexts.
• Prepare model cards and data documentation for all production models. e) Knowledge products and capacity development
• Contribute technical content, worked examples and code notebooks to the GeoInsights for Policymaking practitioner manual.
• Design and deliver at least two technical trainings or workshops for Member State officials and/or ESCWA staff.
• Provide technical input to project proposals, concept notes and briefs involving geospatial and non-traditional data, as requested.
• Mentor DSDS staff and junior consultants and transfer knowledge through documentation, code reviews and hands-on sessions.

A Master's degree or equivalent in geoinformatics, remote sensing, computer science, data science, geography, civil/environmental engineering or a related field is required. A PhD in a relevant field is desirable. A first-level university degree with two additional years of qualifying experience may be accepted in lieu of the advanced degree. All candidates must submit a copy of the required educational degree. Incomplete applications will not be reviewed. At least seven years of progressively responsible experience in geospatial data science, remote sensing or GIS engineering, including at least four years developing and deploying machine learning or deep learning models on Earth observation data is required. Demonstrated experience building production-grade geospatial pipelines on cloud platforms (e.g., Google Earth Engine, AWS, Azure, Planetary Computer) is required. Strong proficiency in Python and the geospatial stack (GDAL, rasterio, xarray, GeoPandas, PostGIS) and in deep learning frameworks (PyTorch or TensorFlow) is required. Experience with segmentation, object detection and time-series analysis of satellite imagery is required. Experience with geospatial foundation models, LLM-based geospatial workflows or MLOps practices is desirable. Experience producing policy-relevant indicators (e.g., SDG monitoring, poverty mapping, economic activity estimation) is desirable. Experience in the Arab region, in international organizations or in conflict-affected settings is desirable. A portfolio of published code, peer-reviewed papers or deployed applications is desirable.

English and French are the working languages of the United Nations Secretariat; and Arabic is a working language of ESCWA. For this position, fluency in English is required and knowledge of Arabic is desirable. Note: “Fluency” equals a rating of ‘fluent’ in all four areas (speak, read, write, and understand) and “Knowledge of” equals a rating of ‘confident’ in two of the four areas.

Not available.

THE UNITED NATIONS DOES NOT CHARGE A FEE AT ANY STAGE OF THE RECRUITMENT PROCESS (APPLICATION, INTERVIEW MEETING, PROCESSING, OR TRAINING). THE UNITED NATIONS DOES NOT CONCERN ITSELF WITH INFORMATION ON APPLICANTS’ BANK ACCOUNTS.