Ph3EO AI Engineer (Agents Integrations) /h3 pOffice location: Rome, Italy – Pi Campus. Full-time position. /p h3Project specifics /h3 ul liEVE (Earth Virtual Expert) is being developed by Pi School, with support from Mistral AI and Imperative Space, for ESA Phi-lab. /li liEVE 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. /li liThe 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). /li liCore workstreams: ul liAgentic framework: tool calling, planning, multi‑agent orchestration. /li liMultimodal expansion: satellite imagery understanding. /li liCommunity ecosystem: open tool registry for EO. /li liESA platform integrations: APEx, EarthCODE, CDSE. /li /ul /li liDiscover more at eve.philab.esa.int. /li /ul h3Responsibilities /h3 ul liIntegrate EO data and services into EVE (STAC, openEO, Copernicus APIs, imagery, weather) behind natural‑language queries. /li liBuild agentic EO pipelines: route queries, break down tasks, call backends, return coherent answers. /li liDesign and wire specialized EO sub‑agents where needed (for example a data‑retrieval agent over CDSE or SentinelHub). /li liSupport integrations with other ESA EO projects and platforms as scoped with the team. /li liHelp the community ecosystem: short tutorials, notebooks, and docs so others can plug tools into EVE. /li /ul h3Requirements /h3 ul liThe 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. /li liEO data formats and standards: GeoTIFF, NetCDF, COG, STAC metadata, CWL/OGC Application Packages, FAIR data principles. /li liSolid Python engineering and experience building data‑intensive applications or pipelines. /li liREST API design and integration with external services. /li liDocker and Linux, including cloud or HPC environments. /li liExcellent proficiency in English. /li /ul h3Bonus points /h3 ul liLLM‑based agents or tool‑using systems (function calling, multi‑step orchestration, prompt engineering for structured outputs). /li liRemote sensing foundation models (Terramind, Prithvi, CLIP‑based EO models). /li liRAG systems (vector databases, retrieval pipelines). /li liSatellite image processing and analysis. /li liCWL workflow authoring or OGC API Processes. /li liOpen‑source contributions in the EO or AI space. /li /ul h3Benefits and Perks /h3 ul liFresh fruit and snacks. /li liAccess to the pool and Turkish bath. /li liSports activities: gym and pilates. /li liFree time in between your tasks to work on your personal projects. /li liAccess to the Pi Campus parties and gatherings. /li /ul h3Diversity /h3 pAt Pi School, we proudly embrace and celebrate each individual’s unique qualities in our team, regardless of race, sexual orientation, gender identity, or other differences. We recognise that these diverse perspectives empower us to overcome challenges, foster innovation, and drive excellence. As an inclusive and equal opportunity employer, we are committed to cultivating an environment where everyone feels welcome, valued, and supported to achieve their full potential. /p /p #J-18808-Ljbffr