Growth Data Scientist
Pubblicato il 13-08-2026 - Edenred in Lombardia
Take a step forward and let Edenred surprise you.Every day, we deliver innovative solutions to improve the life of millions of people, connecting employees, companies, and merchants all around the world. We know there are hundred ways for you to grow. With us, you will expand your skills in a multicultural, challenging, and dynamic environment. Dare to join Edenred and get ready to thrive in a global company that will offer you endless opportunities.Edenred is all about meritocracy. You come as you are, and you contribute. Indeed, the Edenred Group recognizes, recruits and develops all talents and singularities.We are committed to preventing all forms of discrimination and to providing all our candidates with equal opportunities regardless of their gender and gender expression, disability, origin, religious belief and sexual orientation or any other criteria.YOU WILL VIBE WITH USWe are looking for a Growth Data Scientist with proven experience in developing Advanced Analytics and Machine Learning solutions to support business processes,
particularly in the areas of Sales and Customer Management.The successful candidate will work closely with business stakeholders, transforming data and insights into concrete actions while contributing to the adoption of models within operational processes.This role requires a strong combination of technical expertise and business acumen, operating in a hybrid environment that combines model development with their practical application across business functions.Key Responsibilities:Design, develop, and deploy Machine Learning and Advanced Analytics modelsBuild predictive models (e.G., churn, cross-sell, up-sell, propensity models, etc.) and develop the related features and datasetsTranslate models into operational outputs (customer lists, scores, targeting logics) to support commercial processesCollaborate with business stakeholders to understand requirements and translate them into data-driven solutionsMonitor model performance and