Carbon Data Scientist - Rainforest Builder

Your Role:

As a Rainforest Builder data scientist, you will play a central role in the development and monitoring of large-scale tropical forest restoration projects. You will embedded within a dynamic science team working to develop and apply cutting-edge data science solutions to emerging challenges in this space.

You will work closely with Dr Simon Mills, and Dr James Gilroy, and be supported by our Scientific Advisory Board, including Professor Casey Ryan, University of Edinburgh (https://www.research.ed.ac.uk/en/persons/casey-ryan), and Professor David Edwards, University of Cambridge (https://www.plantsci.cam.ac.uk/staff/professor-david-edwards).

You will help to develop Machine Learning approaches that underpin monitoring of our project areas, build and maintain Rainforest Builder’s core data streams, and develop tools that take data from a wide range of data sources (including remote sensing and geospatial data) and provide solutions to emerging business challenges.

You will write clean and scalable code that follows software development best practices to generate products that facilitate project monitoring and help Rainforest Builder to achieve its goals.

What we’re looking for:

This is a group-wide role, and we’re looking for someone ambitious and driven to achieve lasting benefits for climate, biodiversity and local communities through tropical forest restoration at an unprecedented scale.

The candidate will have a graduate qualification (or equivalent experience) in computer science, statistics, or other quantitative science, and be able to provide examples of coding projects that involve data handling and processing through to data analysis and visualisation. Fluency in R or Python is required, as is experience with Git or alternative version control software.

Other desirable experiences include working with Machine Learning methods, handling large geospatial data, and experience working with AWS. You will be practical and adaptable, with an appetite for problem-solving and a good ability to communicate solutions and work collaboratively on data science tasks, while following software development best practices.

Your key responsibilities:

• Contribute to the development and maintenance of RB codebase for data processing and analytics
• Generate insights from geospatial and remote-sensing data, using cutting-edge ML methods.
• Data cleaning: work with a wide range of structured and unstructured data to build clean, tidy, and well-documented data products.
• Produce high-quality data visualisations for communicating insights internally and externally.

Essential qualifications

• Graduate-level qualification (or equivalent experience) in computer science, statistics, or other quantitative science.
• Fluency in R or Python, with experience using Git or other version control software.
• Able to provide examples of coding projects that involve extensive data handling and follow software development best practice.
• Fluency in English (proficiency in additional languages commonly spoken in tropical West Africa is advantageous).

Desirable qualifications

• Experience with Machine Learning methods, particularly with application to geospatial (including remote-sensing) data.
• Experience deploying code on AWS.
• Experience working with Shiny for building dashboards.
• Excellent interpersonal and cross-cultural communication skills, with the ability to collaborate closely on data science tasks and present findings to a generalist audience.
• Commitment to equity, diversity, and inclusion in the workplace and research environment.