AI Research Engineer

Pi School is on a mission to empower businesses and professionals to leverage AI's transformative capabilities. We believe technology should be an enabler, not a barrier, and it should empower individuals and businesses to grow, innovate, and stay connected. We strive for a world where AI and human potential coexist harmoniously, reshaping the way we work, learn, and prosper. Born in 2017 from the expertise of Translated, an industry pioneer with over two decades of leadership in AI + human translation, Pi School has helped over 100 companies integrate AI solutions to improve their operations, enhance decision-making, and achieve sustainable growth.

Pi School remains at the forefront of the ever-evolving AI landscape and collaborates with prominent research centres and organisations worldwide, such as the European Space Agency (ESA) and the European Commission, to harness AI for both cutting-edge research and practical solutions, driving progress in science and beyond. Our approach is founded on purposeful, impactful work, leveraging technology as a force for good.

We are looking for an EO AI Engineer (Agents & Integrations) to work in our office in Rome.

Pi School's AI research team is building EVE (Earth Virtual Expert), an open-source AI platform for Earth Observation, developed for the European Space Agency. We are looking for an engineer at the intersection of EO data engineering and AI-powered agents to help design, build, and integrate EVE's connections to the ESA ecosystem: satellite data catalogues, processing platforms (APEx, EarthCODE), Copernicus services, and geospatial tooling.

• 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 (for example GitHub, the Hugging Face Hub, and 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.

You will be part of Pi School's AI Research team full-time, building the agentic layer at the heart of EVE. In this role, you will:

• Design and implement EVE's agent orchestration with LangGraph: planning, tool calling, state and memory management, and multi-agent workflows.
• Build and maintain MCP servers and clients so EVE can use EO tools and services (data catalogues, processing platforms, community tools) through a common interface.
• Implement agent-to-agent communication with A2A, so EVE can delegate to specialised sub-agents and interoperate with agents from other ESA projects and partners.
• Design specialised sub-agents (for example a data-retrieval agent over CDSE) and the routing logic between them.
• Evaluate and improve agent behaviour: tool-use accuracy, task success, robustness, and latency.
• Follow the state of the art in agentic systems and turn promising ideas into working prototypes, open releases, and publications.
• Help the community ecosystem: short tutorials, notebooks, and docs so others can plug tools and agents into EVE.

Hands-on experience with:

• LangGraph: building stateful, multi-step or multi-agent applications beyond simple chains.
• Model Context Protocol (MCP): writing MCP servers and/or integrating MCP tools into agents.
• Agent2Agent (A2A) protocol: agent cards, task delegation, and communication between independent agents.
• LLM-based agents and tool-using systems more broadly (function calling, structured outputs, multi-step orchestration).
• Solid Python engineering.
• Excellent proficiency in English.

• Backend development and API design.
• FastAPI.
• Qdrant or other vector databases.
• Cloud compute or HPC environments.

Pi School is hosted at Pi Campus, a working environment immersed in nature. Six luxury villas in Rome (Italy) have been converted into functional offices to foster talent growth. Pi Campus is also a venture firm created by Translated to reinvest part of its profits into promising AI startups.

Based on a standard level of experience, the offered salary typically ranges between €35.000,00 and €55.000,00. The actual package depends on factors such as location, scope of responsibilities, and performance. Compensation generally grows quickly as experience leads to greater contributions. Exceptionally strong candidates may be offered salaries above this range to acknowledge their higher potential impact.

Starting date: as soon as possible

Appplication deadline: 31 December 2026

Our working environment is both relaxed and intense. We are passionate about our mission, and our work is highly regarded in our industry.

• Fresh fruit and snacks
• Access to the pool and Turkish bath
• Sports activities: gym and pilates
• Free time in between your tasks to work on your personal projects
• Access to the Pi Campus parties and gatherings

Learn more about our company: https://picampus-school.com/.

At 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.