Machine Learning Scientist: Electrochemical Product Authentication (KTP Associate)

The main purpose of the role is to lead the development, validation and implementation of statistical, chemometric and machine learning approaches that enable Eluceda to authenticate products quickly and reproducibly without the need for added markers. The KTP will focus on extracting reliable, decision-ready information from complex electrochemical sensor datasets generated by Eluceda’s handheld detection technology.

You will develop methods to compare, classify and discriminate between genuine and counterfeit products, with initial applications including spirits and pharmaceutical products. The work will include data organisation, preprocessing, exploratory analysis, multivariate modelling, pattern recognition, model validation and the development of a user-friendly software workflow that can be used by Eluceda staff and, ultimately, support customer-facing applications.

The role will require close collaboration with Eluceda’s scientific, technical and commercial teams, as well as academic supervisors at the University of York. You will be expected to translate advanced statistical and machine learning methods into practical tools, documented procedures and embedded company capability, supporting one of Eluceda’s strategic aims of becoming a market leader in marker-free product authentication.