Ocean Computer Vision Scientist – National Oceanography Centre, Southampton

Who are we?

We are the National Oceanography Centre (NOC) – the UK’s centre of excellence for oceanographic sciences. We are a national research organisation, delivering integrated marine science and technology from the coast to the deep ocean.

We are made up of a dynamic and vibrant community whose focus is on improving the world in which we live. Our work is balanced by our strong sense of purpose, values and behaviours and an unwavering commitment to a ‘one NOC’ approach.

We have a rich history dating back to 1949, and our future has never looked more exciting as we aim to be the world’s most innovative oceanographic institution.

About the role

You will be joining a dynamic and innovative research group in the quest of developing intelligent image data processing methods to enable us to understand what drives plankton, sinking particles, and hence ocean carbon storage. 

You will help to develop and evaluate the performance of user-friendly plankton and particle image classification using machine learning. Using field data, you will explore whether we can predict sinking velocities from images using mixed data model architectures. You will be actively involved in shaping the image processing pipeline at NOC from in situ collection to data interpretation, working closely with biological oceanographers. Your role includes the collaboration with engineers and ecologists to improve camera systems and image processing, including combining multiple camera systems to image the full plankton size spectrum (from µm to cm). Camera systems will include commercial photographic and holographic systems as well as custom-built systems.

You will have the opportunity to do fieldwork at sea. 

You will be a key member of a versatile project that goes from engineering (including camera system calibration and deployment) to biogeochemistry (including lab work) via image analysis (machine learning, AI) to mathematically describing particle flux.

About you

You are excited to join a dynamic team and produce cutting-edge high-quality scientific outputs. You are independent, curious, creative and like versatile work. You like solving problems and taking the initiative in challenging situations. At the same time, you like working closely with your team members. 

You have a sound understanding of machine learning and image classification. Ideally, you have experience in plankton and particle imaging. You know and enjoy using programming languages (e.g. R, Matlab, Python), and you like to help others in their quest of using them. Ideally, you have experience working with larger and complex data sets.

Why the NOC?

We offer a generous set of benefits including 28 days annual leave, plus 3.5 local closure days and 8 public bank holidays, and a contributory Group Personal Pension Plan.

We are committed to flexible working, trusting our staff to get the job done. And we offer an inclusive and supportive environment where our people can meet their full potential.

The centre is well connected by public transport and has ample cycle parking in addition to free onsite car-parking. We support opportunities for further training and development.

Our commitment as an employer

The NOC is an equal opportunities employer and welcomes applications from all sections of the community. There is a guaranteed interview scheme for suitable candidates with a disability and we welcome applications from ethnic minorities currently under-represented. The NOC is an Investors in People organisation, and has signed up to the Athena SWAN charter principles to take action to address gender equality.

How to apply: 

Please click ‘Apply for this job’ and submit an up-to-date CV and cover letter. If you are unable to apply online, please contact the NOC recruitment team at careers@noc.ac.uk / 07955 851648.

https://careers.noc.ac.uk/internal/vacancy/ocean-computer-vision-scientist-454182.html

Leave a Reply

Your email address will not be published.

*

This site uses Akismet to reduce spam. Learn how your comment data is processed.