The FOSTER programme’s enhanced internship scheme provides students an opportunity to gain work experience within the growing UK fusion industry. The FOSTER programme is looking to build the talent pipeline into the industry. Over the past three years, 83 students have participated in placements in 20 host organisations around the UK, with many receiving offers of employment after their graduation.
Tokamak Energy are fully committed to building talent within the fusion industry and excited to offer internship opportunities across our business. The placement will give you valuable experience working within a commercial fusion company alongside talented experts within the field, building both your technical and business knowledge.
Placements at Tokamak Energy also give students the opportunity to regularly collaborate not only with our employees, but crucially with other members of your cohort. We recognise the value of creating a supportive learning environment to enable you to explore the subjects and skills that you are passionate about. This is your chance to dive into the world of Fusion Energy and help shape the future of sustainable energy!
With irradiated materials, there is often a sparsity of property data because of the significant expense, time scale, and complexity of irradiation testing and post-irradiation characterization. This role is aimed at developing machine learning tools that can be used to either enhance the collection of data from open literature or improve the analyse of sparse datasets.

REQUIREMENTS

• Required: knowledge of programming language(s) useful to machine learning such as Python.
• Required: knowledge of algorithms for machine learning such as Gaussian processes, gradient boosting, K-means, random forest, etc.
• Required: communicating and relating with others (oral/written)
• Valued: experience with database structures.
• Valued: understanding of thermo-mechanical, electro-magnetic, neutronic, and irradiated material properties.

• Write machine learning algorithms for data scrapping or advanced data analysis.
• Train and test machine learning algorithms with materials property data.
• Develop workflows to interface with the TE materials database.
• Develop standards for the evaluation of data quality.