Senior Data Scientist

Key Responsibilities

• Own machine learning problems, models and components end-to-end across recommendations, ranking, personalisation, customer modelling and predictive modelling.
• Partner with Product, Commercial, Marketing and other stakeholders to identify high-value opportunities, shape ambiguous problems and determine whether Data Science is the right intervention.
• Independently select, build and improve modelling approaches, using feature engineering, tuning and appropriate algorithmic choices to improve performance.
• Design robust offline evaluation strategies, selecting metrics that reflect problem-specific behaviour and trade-offs rather than relying solely on generic model-performance measures.
• Design and support online experiments to evaluate real-world impact, working with Product and Analytics partners to define success metrics, guardrails and appropriate interpretation of results.
• Own outcomes beyond model delivery: follow solutions through production and experimentation, determine whether they are creating the intended customer or commercial impact and drive iteration where they are not.
• Design components of machine learning systems, such as feature-generation pipelines, model-scoring logic and inference workflows, working closely with Engineering to integrate solutions into production.
• Collaborate with MLOps to deploy models and ensure appropriate monitoring, retraining and operational processes are in place, addressing issues such as drift, data-quality problems and performance degradation.
• Write high-quality, tested and maintainable Python and SQL, contributing robust and reproducible solutions to shared production codebases.
• Build practical AI-powered features where appropriate, such as solutions using prompts, embeddings or other generative AI capabilities, and evaluate their outputs systematically.
• Use AI-assisted development tools to improve coding, analysis, experimentation and documentation, critically evaluating outputs and identifying opportunities to improve team workflows.
• Communicate technical decisions, model behaviour, trade-offs and recommendations clearly, using evidence to influence product and business decisions and prioritisation.
• Contribute to the wider Data Science capability through informal mentorship, peer review, knowledge sharing, reusable tooling and improvements to technical practices and ways of working.

About You

• Strong experience developing and delivering machine learning solutions in a Data Science, Machine Learning or closely related role, including ownership of models or substantial ML components.
• Strong practical understanding of supervised machine learning, feature engineering, model selection, tuning, validation and evaluation, with experience independently improving model performance.
• Strong Python and SQL skills, with experience developing robust Data Science solutions in shared production codebases.
• Ability to take ambiguous customer or business problems, determine an appropriate Data Science approach and independently drive the work through to a usable solution and understood outcome.
• Strong experience designing offline evaluation approaches and selecting metrics that appropriately reflect model performance and problem-specific trade-offs.
• Experience designing, analysing and interpreting online experiments, with the ability to connect technical model performance to customer and commercial outcomes.
• Experience deploying or contributing significantly to the deployment of machine learning models, with a good understanding of monitoring, retraining, data quality, model drift and common production issues.
• Experience designing components of machine learning systems, such as feature pipelines, scoring logic or model workflows, and working effectively with Engineering to integrate them into production.
• Strong understanding of testing, version control, reproducibility and maintainable software-development practices within a Data Science environment.
• Able to make sound technical decisions independently and clearly articulate the trade-offs between alternative modelling, evaluation and implementation approaches.
• Able to communicate complex technical concepts, assumptions and recommendations clearly and use evidence to influence Product, Engineering and business stakeholders.
• Effective use of AI-assisted development tools to improve coding, analysis and experimentation, combined with strong judgement around validation, privacy, security and responsible use.
• Strong awareness of data quality, privacy, fairness, security and customer-experience considerations when designing and deploying machine learning solutions.
• Experience developing recommendation, ranking or personalisation systems would be beneficial.
• Experience with customer modelling approaches such as propensity, uplift or customer lifetime value modelling would be beneficial.
• Experience applying LLMs, embeddings or other generative AI techniques to build practical product or Data Science features would be useful.
• Experience working in a B2C e-commerce, retail or other high-volume digital product environment would be useful.
• Experience working with cloud-based machine learning infrastructure and services, particularly AWS, would be beneficial.
• Familiarity with analytics engineering tooling such as dbt would be useful.
• Experience with large-scale or near-real-time ML systems would be beneficial.
• Experience mentoring junior team members, supporting peer review, sharing knowledge and acting as a key source of technical support would be beneficial.
• A degree in Statistics, Mathematics, Economics, Computer Science or another relevant quantitative discipline can be helpful, but equivalent practical experience is equally welcome.

Our Tech Environment

• Python and SQL for developing robust Data Science solutions.
• AWS for cloud-based machine learning infrastructure and services.
• ML systems spanning feature-generation pipelines, model-scoring logic and inference workflows.
• Production ML practices covering deployment, monitoring, retraining, data quality and model drift.
• Offline evaluation and online experimentation to connect model performance with customer and commercial outcomes.
• Generative AI capabilities including prompts, embeddings and other practical AI approaches.
• AI-assisted development tools across coding, analysis, experimentation and documentation.
• dbt within our wider analytics engineering tooling.

How We Get There

Interview Process

Following an initial recruiter screening, the expected process includes a Hiring Manager Interview, Technical Screening, Technical Interview Follow-up and Final Round.

The exact structure is still being confirmed, and we’ll keep candidates informed of any changes throughout the process.