Industrial Placement 2025 - Urban-scale Artificial Intelligence Modeller

at  Met Office

Job Introduction
The Met Office is delighted to open our advertising for a number of Industrial Placements, which will commence from July 2025 until July 2026.
We’re looking for an exceptional Urban-scale Artificial Intelligence Modeller Industrial Placement to help us make a difference to our planet.
This is an exciting opportunity to join the Met Office on a 12-month Year in Industry placement, developing your skills and knowledge and ensuring you gain the most value possible from your experience with us. You will have the opportunity to network with our cohort of Industrial Placements all over the Met Office and understand what career opportunities we can offer you after you graduate.
As our Urban-scale Artificial Intelligence Modeller, the job may be suitable for hybrid working, which is where an employee works part of the week in the office and part of the week from home. This is a voluntary, non-contractual arrangement and the location advertised will be your contractual place of work.
Our opportunity is full time, 37 hours per week. Our people are at the heart of what we do and we’ll do our best to agree a working pattern that works for everyone.

ESSENTIAL CRITERIA, SKILLS AND EXPERIENCE:

• Have basic programming ability and be keen to develop Python, GitHub, and ML skills, embodying our value “we keep evolving”
• Be a team player that is happy to collaborate and is pro-active in seeking advice, exemplifying our value “we’re better together”
• Be motivated to use cutting-edge science for positive societal impact, reflecting our values “we’re experts by nature” and “we’re a force for good”

• Develop an ML method for downscaling precipitation from kilometre- to hectometre-scale, using 300 m ensemble simulations from the WesCon field campaign as training data. There is the potential to extend this to downscaling of other variables.
• Adapt existing ML workflows (using Python and the Azure platform) to design a new ML workflow that is under GitHub version control.
• Identify and apply appropriate techniques to evaluate the performance of the emulator.
• Deliver a report documenting the background literature, the ML workflow, and the research findings. Present the main results from this at an RMED team brief.