Research Fellow in Artificial Intelligence for Earth Observation


Fellowship Fixed Term Frascati, Italy

Uploaded 25 Jun 2020

Job Description

Our Team and Mission

You will be based in the Φ-lab in ESRIN, whose mission is to accelerate the future of Earth Observation (EO), by helping ESA and the European industry, startup and research communities to rapidly adopt disruptive technologies. You will be part of a multi-disciplinary team of researchers and data scientists passionate about innovation, and work within an inspiring and collaborative open-space environment.

Interested candidates are highly encouraged to visit the ESA website:

Fields of research and activities

You will carry out research in the field of Artificial Intelligence (AI) with a particular emphasis on developing new methods applicable to Earth Observation (EO). The specific area of research is partly chosen by you based on your own expertise and partly chosen by the team as to follow strategic directions of the Agency.

In particular, you will:

  • perform your own research, while also contributing to the lab current AI4EO use cases (e.g. multi-sensor data fusion, edge computing, automatic change detection, transfer learning, mining of hyperspectral data);
  • support the team rapidly prototype and evaluate AI solutions for application to EO data sets and challenges, particularly those relevant for ESA EO missions;
  • adapt existing AI algorithms and tools to take account of the specific characteristics of EO data sets, physical measurement principles, and apply them to EO data applications with particular interest in hyperspectral imaging and radar imaging;
  • prepare, validate and maintain large-scale, training data sets, to be used for development and evaluation of AI algorithms, by international research and industrial communities;
  • contribute to the development of an interactive environment for rapid prototyping and testing of new ideas;
  • organise and lead AI4EO challenges on proposed topics;
  • collaborate with academia and industrial partners to transfer research results to applications;
  • publish in peer-review literature;
  • promote/share your results and tools through new digital tools, including social media and Jupyter notebooks;
  • perform and participate in assessments on subjects of strategic interest to ESA.

Person Specification

Technical competencies

  • Knowledge relevant to the field of research
  • Research/publication record
  • Ability to conduct research autonomously
  • Breadth of exposure coming from past and/or current research/activities
  • General interest in space and space research

Behavioural competencies

  • Innovation & Creativity
  • Continuous Learning
  • Communication
  • Relationship Management
  • Self Motivation
  • Problem Solving
  • Cross-Cultural Sensitivity

Applicants should have recently completed, or be close to completion of a PhD on AI, Computer Science or Machine Learning, with the subject of the thesis being relevant to the description of the tasks outlined above . Preference  will  be  given  to applications submitted by candidates within  five  years of receiving their PhD.


Applicants must have obtained:

  • A degree in either AI, computer science, mathematics or relevant engineering discipline.

Additional requirements

  • In depth knowledge of themes of interest, such as EO, AI, analytics, and New Space;
  • Proven experience leading research, with international recognition;
  • Ability to think outside the box and explore new avenues, with natural curiosity and a passion for new subjects and research areas;
  • Ability to work in a multicultural environment as part of a team;
  • Experience with one or more general purpose programming languages e.g. Python, and with general purpose deep learning frameworks e.g. Tensorflow, PyTorch;
  • Natural curiosity and a passion for new subjects and research areas, including AI, EO, and New Space.

The working languages of the Agency are English and French. A good knowledge of one of these is required. Knowledge of another Member State language would be an asset.