Senior Data Scientist – Applied Machine Learning

Translate customer and business problems into clear analytical and machine-learning objectives.
Work with large datasets, event data and feature stores to identify useful signals and build predictive features.
Develop, evaluate and improve models for use cases such as propensity, personalisation, growth and retention.
Apply appropriate techniques across classification, regression, experimentation, forecasting and other applied data-science problems.
Take models through the full product lifecycle, including deployment, automation, monitoring, retraining and ongoing maintenance.
Help improve data quality, feature pipelines, model monitoring, drift detection and ML Ops practices.
Work with product managers and business stakeholders to define success measures and translate model outputs into action.
Explain technical approaches, assumptions and results clearly to technical and non-technical audiences.
Collaborate with data, software and AI engineering teams to review solutions, improve coding standards and share knowledge.
Contribute to technical documentation, design discussions and delivery planning.
Work with external partners or vendors where required to deliver the right solution.
Commercial experience as a Data Scientist, Applied Scientist, Machine Learning Engineer or in a closely related role.
Strong Python skills and experience writing maintainable, tested and production-quality code.
Strong foundations in probability, statistics, model evaluation and machine-learning fundamentals.
Practical experience with classification, regression, feature engineering and experimentation.
Experience developing, deploying and maintaining machine-learning models in a cloud environment such as Databricks, AWS SageMaker, Azure ML or an equivalent platform.
An understanding of data pipelines, feature stores, data quality, model monitoring, drift and retraining.
Experience working across the full model lifecycle, from problem definition through to production and ongoing improvement.
The ability to work effectively with product managers, engineers, analysts and senior business stakeholders.
A collaborative approach to code reviews, documentation, knowledge sharing and continuous improvement.
Good judgement about when to use a simple, explainable approach and when a more advanced technique is justified.
It would be useful if you also have
Experience with generative AI, large language models or agentic AI applications.
Experience with recommendation systems, personalisation or customer propensity modelling.
Experience with natural language processing, time-series forecasting or financial modelling.
Experience with MLflow, Git-based CI/CD, dbt or related data and ML engineering practices.
Experience with R or Scala.
Experience presenting data and model outputs using tools such as Streamlit, Power BI or Tableau.

Employment type
Full-time

Work arrangement
Hybrid