Intern in the Science Operations Department, A Copilot for ESA Datalabs

Our team and mission

This position is based at the European Space Astronomy Centre  (ESAC) - Near Madrid, Spain

Under the direct authority of the Directorate of Science, the Head of the Science Operations Department is responsible for the development of the science operations infrastructure under the Directorate responsibility, the operation of the Directorate’s missions once successfully commissioned, and the curation of all scientific data in the missions’ legacy phase. These responsibilities are discharged in full coordination with the Directorate’s Departments and Offices and as appropriate, with the Directorate of Operations (D/OPS). 

In implementing its duties, the Science Operations Department is supported by the:  

• Mission Management and Science Operations Division (SCI-SO); 
• Science Operations Development Division (SCI-SD); 
• Data Science and Archives Division (SCI-SA). 

Candidates interested are encouraged to visit the ESA website: http://www.esa.int

Field(s) of activity for the internship

Topic of the internship:  A copilot for ESA Datalabs

Natural Language Processing (NLP) techniques have recently gained traction in astronomy with the rise of Large Language Models (LLMs). LLMs have been employed in various applications, such as tailoring models specifically for astronomy (Dung Nguyen et al., 2023), in scientific publications (Astarita et al., 2024), and creating query-based chat bots like Pathfinder (Iyer et al., 2024).

In previous work, we have been developing a Retrieval-Augmented-Generation (RAG) pipeline for integrating open-source LLMs with scientific publications and internal documentation. The objective of this project is to deploy such a RAG pipeline in the ESA Datalabs science platform and to explore its use with an open-source LLM for code, such as Codestral (https://mistral.ai/news/codestral/), to provide a free coding assistant for users. This tool, integrated with the collaborative features of Jupyter Notebooks, would be incredibly powerful feature for the users of the platform.

Behavioural competencies

Result Orientation
Operational Efficiency
Fostering Cooperation
Relationship Management
Continuous Improvement
Forward Thinking

For more information, please refer to ESA Core Behavioural Competencies guidebook

Education

You must be a university student, preferably in your final or second-to-last year of a university course at Master’s level and you need to remain enrolled at your University for the entire duration of the internship.

Additional requirements

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.

• Knowledge of natural language processing;
• Knowledge of open-source large language models;
• Experience with python programming and Jupyter notebooks;
• Familiar with software engineering concepts and version control; 
• Background coursework in computer science or data science would be a plus.