Machine Learning Scientist: Foundation Models
Machine Learning Scientist: Foundation Models
BAS - British Antarctic Survey
Cambridge, United Kingdom
British Antarctic Survey (BAS) is looking for an exceptional machine learning engineer/researcher to join the AI team. Initial focus will be to develop and deploy groundbreaking self-supervised foundation models for the automated detection of sea ice conditions in satellite imagery. You will become an integral member of an international collaboration of researchers quantifying the uncertainty in the historical passive microwave derived sea ice data record. This dataset is used extensively in by scientists, the media, local communities, industry, and policy makers, making the quantification of its uncertainty of unequivocal importance. You will have the opportunity to work in close collaboration with our partner organisations, including: The Alan Turing Institute, Norwegian Ice Service, and the United States National Snow and Ice Data Centre.
Working at BAS is rewarding. Our skilled science, operational and support staff based in Cambridge, Antarctica and the Arctic, work together to deliver research that uses the Polar Regions to advance our understanding of Earth as a sustainable planet. Through our extensive logistic capability and know how BAS facilitates access for the British and international science community to the UK polar research operation. Numerous national and international collaborations, combined with an excellent infrastructure help sustain a world leading position for the UK in Antarctic affairs. British Antarctic Survey is a component of the Natural Environment Research Council (NERC), which is part of UK Research and Innovation.
You’ll be joining the BAS AI Lab, a team of machine learning researchers, research software engineers, and remote sensing specialists developing state-of-the-art machine learning tools and digital frameworks to improve our understanding of the Earth’s Cryosphere and its response to climate change. Within this, you’ll form part of the Artificial Intelligence for Environmental Imagery (AIEI) group, working collaboratively with scientists across BAS and beyond to apply computer vision techniques to environmental datasets.
Current projects the team are working on include (among others):
- IceNet: IceNet is a deep-learning sea ice forecasting system developed by an international team of researchers and software engineers, led by BAS and the Alan Turing Institute (ATI)
- DeepSensor: DeepSensor is a python package and open-source project developed by BAS and ATI for modelling environmental data using convolutional neural processes.
- Autonomous Marine Operations Planning (AMOP): This project is developing a suite of Artificial Intelligence (AI) methods that aim to optimise the efficiency of Antarctic field operations and provide decision support for management of the BAS marine fleet including our research ship the RRS Sir David Attenborough.
- DEFIANT: This major NERC-funded international collaboration is identifying the drivers and effects of sea ice fluctuations in the Antarctic.
Within the role, you will be collaborating with a group of scientists, software engineers, and machine learning researchers spanning BAS, Alan Turing Institute, US National Snow and Ice Data Centre, Norwegian Ice Service and beyond. You will be building a groundbreaking self-supervised foundation model for the automated detection of sea ice in satellite imagery.
We offer significant support and guidance in applying for funding, including a tailored mentorship scheme for fellowship applications. Training is available on in-house models and techniques where required, and more broadly on skills for career development such as grant writing and scientific leadership.
Some of your main responsibilities will include:
- To train and deploy a self-supervised foundation model of the polar regions to automatically generate high resolution SIC (SIC-HR) products from satellite imagery.
- Collaborate with national and international colleagues to quantify the uncertainty in the passive microwave sea ice concentration record using these SIC-HR products.
- Explore potential future collaborations for the wider application of the polar foundation model developed.
For the role of Machine Learning Scientist: Foundation models, we are looking for somebody who has:
- A PhD in a relevant field, plus post-doctoral experience. Equivalent relevant experience will be considered.
- Expertise in developing and training state-of-the-art machine learning tools.
- Proficiency in one or more modern statistical programming languages used in research in data science and machine learning, such as Python.
© EuroJobsites 2024
