Our client, a renowned European institution in Seville, Spain, is the European Union’s science hub. They are responsible for providing technical information and data in support of key European policies like innovation, economic modelling, fiscal policy, digitalisation, and artificial intelligence.
We are seeking a skilled Data Scientist who will play a key role in a forefront geographic information system project that aims to analyse decarbonisation data for energy-intensive industries.
Contract type offer:
Freelancer (short-term contract)
Location requirement:
Seville, working from the Institution’s comfortable offices.
Description of the tasksExtract, clean, and structure information ( related to emission reductions/sustainability targets, actions/ decarbonisation levers, investments information, etc.) from various Climate Transition Plans (CSRD reports).Develop a semi-automated process to scale up the extraction from an increasing number of PDFs climate reports over time (leveraging AI LMM and machine learning)Conduct data analysis to complement the dataset with publicly available data(e.G. press released) or private databasesExplore and propose options to scale up the database from an EU-centric approach to a Global approachDesign and implement routines and procedures for updating and backing up the datasetPropose and implement IT solution to connect the database to the existing preliminary version of the analytical toolPerform analysis at corporate, sectoral, or geographical level (local, regional, country) to identify trends, patterns, and statistical insights (using data analysis tools and techniques)Create visual representations on maps (e.G., with GIS, Tableau, or Power BI)Based on the analysis performed, propose new features for improving the GIS tool and implement themUpdate the underlying data sources included in the GIS tool
Knowledge and skillsExperience with building data pipelines to extract, clean and structure data from diverse sources (e.G. PDFs, databases, APIs)Experience with database management and design (e.G. relational databases, NoSQL databases)Strong programming skills in languages such as R, Python is requiredAbility to work with large datasets and perform data quality checksExperience with data visualisation and communication of complex data insights to non-technical stakeholdersKnowledge of machine learning and AI techniques, particularly in natural language processing (NLP) and text analysisFamiliarity with geospatial analysis and mapping tools such as GIS, Tableau, or Power BIStrong analytical and problem-solving skills, with the ability to identify trends, patterns, and statistical insights in large datasetsExperience or understanding of climate-related dataFamiliarity with cloud-based data platforms and services (e.G. AWS, Google Cloud, Azure)
Bachelor's or Master's degree in a relevant field such as Computer Science, Data Science.