Applied Scientist - Forecasting

We're looking for an Applied Scientist to join our AI Demand Forecasting team. Our mission is to build forecasting capabilities that support critical business decisions across the company. While our foundations are in replenishment forecasting, we're evolving into a forecasting platform that provides scalable, high-quality demand forecasts for a growing range of use cases, including AI-powered Pricing and Supply Chain optimisation. This means tackling challenging machine learning problems while building reusable forecasting capabilities that can be applied across multiple domains. As an Applied Scientist, you'll work alongside data engineers, ML engineers, analysts, product managers, and business stakeholders to design, develop and deploy machine learning models at scale. You'll have the opportunity to influence both the scientific direction of our forecasting systems and the products that depend on them. Key Responsibilities - Design, develop and deploy machine learning models for demand forecasting in production environments. - Improve forecasting accuracy, robustness, scalability and explainability across diverse business use cases. - Develop forecasting solutions that support multiple downstream consumers, including replenishment, pricing and supply chain optimisation. - Design and analyse offline and online evaluations to measure model performance and business impact. - Collaborate closely with engineers to productionise models and build reliable, scalable ML systems. - Explore and evaluate new modelling approaches from industry and academia, testing and prototyping promising ideas. - Contribute to the team's scientific direction through technical discussions, code reviews and knowledge sharing. About You You'll enjoy applying machine learning to large-scale, real-world forecasting challenges and translating research into production systems. We'd be particularly interested in candidates who bring experience in some of the following areas: - Developing and deploying machine learning models in production environments. - Applying statistics, analytics and machine learning techniques to solve real-world problems. - Experience in one or more of the following areas: - Time series forecasting - Probabilistic forecasting - Deep learning - Gradient boosting - Causal inference - Optimisation - Proficiency in Python and modern machine learning frameworks such as PyTorch, TensorFlow or similar. - Working with large datasets and distributed data processing systems. - Software engineering practices including testing, version control and writing maintainable code. - Communicating technical concepts to both technical and non-technical audiences. - Curiosity, pragmatism and a willingness to learn, experiment and share knowledge.