We’re looking for an experienced senior technical leader for our science and machine learning efforts who has a unique combination of talents and experience. The essence of this role is to fully internalize Earthshot’s vision for heart-led planetary regeneration, formulate truly groundbreaking ways to apply machine learning models in order to realize this vision, and to attract, inspire and support a world-class technical team in order to build this technical vision. We seek someone who has deep knowledge of neural architectures and a range of experiences applying deep learning systems to solve challenging real world ecological problems. The ideal candidate would have a wealth of experience sourcing, onboarding, and feature engineering remote sensing geographical information sources, notably various forms of satellite and aerial imaging data. Thirdly our ideal candidate would have knowledge of and experience working with land surface simulation models applied to forest ecology and other relevant biomes and ecological processes. Our chief data scientist should have a combination of extensive academic and commercial experience, able to draw upon a strong support network and to attract world class technical talent from both realms. They should be equally versant in putting together state of the art research plans, and delivering enterprise quality software products. The Chief Data Scientist will oversee a fast growing team of machine learning engineers, remote sensing data specialists, forest ecologists, and other specialized technologists and thus should have excellent relational, communication and technical team leadership skills. This role will work directly with the founders of the company, most notably the CTO, in order to realize and expand upon Earthshot’s ambitious vision.
Requirements:
- 10 + years experience working with data and machine learning models, including and ideally focused on deep learning architectures. Academic research experience may count for a portion of this, in addition to industry software development experience.
- Experience applying deep learning architectures to real world problems; knowledge of different forms of ANN’s, experience with feature engineering, hyperparameter tuning, and other aspects of model development and refinement
- Comprehensive knowledge of remote sensing data sources and their application to ecological modeling. Ability to formulate hypotheses around these data sets and rapidly validate them.
- Experience with leading software development teams to deliver enterprise grade products, ideally applying deep learning to solving truly challenging problems
- Expertise in Python, R or other commonly used machine learning languages
- A deep love for nature and desire to help build a more integrated future for humanity within it