Scientific Data Engineer

at  Vito

To enforce VITO’s remote sensing unit, we’re looking for a scientific data engineer to build services and thematic applications. Together with the team you will support remote sensing projects that are executed on openEO, which is an open-source cloud-based service for the processing of huge satellite imagery datasets. You will collaborate with data scientists and researchers that are experts in their fields. This position gives you the opportunity to work on projects with global visibility, focused on supporting the green transition towards a sustainable planet. Your work is used by the European Commission and the European Space Agency, who rely on it to provide timely and accurate information to experts working in the field, trying to have local impact while ensuring global food security or fighting climate change.
You’ll become part of a talented, dedicated team working in a fast-paced, challenging international environment. A strong technical background in Python programming and data engineering in general is required to support these projects. Knowledge of earth observation or computer vision applications is a plus, but fast learners that are interested in exploring this domain are more than welcome to apply.
Most application-oriented projects use a form of machine learning to extract information from satellite or drone imagery. In this role, you continuously interact with internal and external teams that look for efficient ways to train their models and want to run them in production.
You implement techniques such as ML Ops to make these projects run smoothly and efficiently. A keen eye for constant improvement is a must to be successful in your role.
The Remote Sensing unit of VITO, as part of the larger Environmental Intelligence unit, processes petabytes of earth observation data. We primarily specialize in Big Data analysis with the use of machine learning and deep learning techniques in the application workflows. That is our passion: the extraction of ready-to-use information from the vast amounts of incoming images. Our extensive group of clients can be found within the domains of land use, biodiversity, agriculture, forestry, water management, and civil infrastructure.

Your responsibilities:

• You are part of a team of software engineers to develop efficient algorithms, models, back-end extensions, and proof of concepts, with a hands-on mentality.
• Engage with architects, thematic experts and project owners to translate their project requirements into data pipelines/workflows and make these run efficiently.
• Use the openEO ecosystem to create production workflows, analytics applications, and data visualization.
• Implement continuous improvements and maintenance activities in workflows and processes.
• Keep track of the latest developments and technologies in the software, AI and remote sensing world to be able to remain state-of-the-art in our domain.

Must have:

• You hold a Master’s degree in sciences or engineering, specialized in computer science or equivalent
• You have profound knowledge in Python programming
• You have experience in Continuous Integration, Testing & Automation frameworks
• You have a excellent command of English (Dutch is a plus)
• You are a teamplayer and you are self-organized
• You’ve got an engaging personality and good communication skills
• Strong analytical skills are crucial given that you will join an ambitious team confronted with constantly evolving IT and Earth Observation business needs.

Nice to have:

• Proven experience with data engineering
• Understanding of different remote sensing data sets such as the Copernicus Sentinel satellites
• Experience in cloud native deployments
• Experience in large scale data processing (e.g. Spark)

• You are part of a team of software engineers to develop efficient algorithms, models, back-end extensions, and proof of concepts, with a hands-on mentality.
• Engage with architects, thematic experts and project owners to translate their project requirements into data pipelines/workflows and make these run efficiently.
• Use the openEO ecosystem to create production workflows, analytics applications, and data visualization.
• Implement continuous improvements and maintenance activities in workflows and processes.
• Keep track of the latest developments and technologies in the software, AI and remote sensing world to be able to remain state-of-the-art in our domain