Earth Observation AI Engineer
Pubblicato il 21-08-2026 - Pi School in Italia
EO AI Engineer (Agents & Integrations)
Office location: Rome, Italy – Pi Campus. Full-time position.
Project specifics
- EVE (Earth Virtual Expert) is being developed by Pi School, with support from Mistral AI and Imperative Space, for ESA Phi-lab.
- EVE is evolving from a text‑based EO assistant into a multimodal, agentic platform under ESA Phi-lab, serving as Europe’s main knowledge nexus between Earth AI models, data, tools, and resources.
- The project is fully open source, with the aim of publishing code, models, and documentation across several public venues (GitHub, Hugging Face Hub, ESA Phi‑lab).
- Core workstreams:
- Agentic framework: tool calling, planning, multi‑agent orchestration.
- Multimodal expansion: satellite imagery understanding.
- Community ecosystem: open tool registry for EO.
- ESA platform integrations: APEx, EarthCODE, CDSE.
- Discover more at eve.philab.esa.int.
Responsibilities
- Integrate EO data and services into EVE (STAC, openEO, Copernicus APIs, imagery, weather) behind natural‑language queries.
- Build agentic EO pipelines: route queries,
break down tasks, call backends, return coherent answers.
- Design and wire specialized EO sub‑agents where needed (for example a data‑retrieval agent over CDSE or SentinelHub).
- Support integrations with other ESA EO projects and platforms as scoped with the team.
- Help the community ecosystem: short tutorials, notebooks, and docs so others can plug tools into EVE.
Requirements
- The EO/geospatial stack: STAC, openEO, OGC APIs, CDSE or SentinelHub, Google Earth Engine, xarray, rasterio, or similar. Comfortable navigating satellite data catalogues and processing pipelines.
- EO data formats and standards: GeoTIFF, NetCDF, COG, STAC metadata, CWL/OGC Application Packages, FAIR data principles.
- Solid Python engineering and experience building data‑intensive applications or pipelines.
- REST API design and integration with external services.
- Docker and Linux, including cloud or HPC environment