The Data Science and Analytics team builds data-driven tools that support ethical and commercially sound decisions across the company's books.
This is a 12-month fixed-term contract. You will help the business make better decisions from data over the full life of a book. Current work includes demand and pricing models, recommender systems that drive automated marketing, and AI tools for market analysis and summarisation. The team covers the whole list, from frontlist bestsellers to long-tail backlist, and supports colleagues in Sales, Marketing, Digital and Editorial.
Your focus will be two current priorities: pricing and recommender-driven marketing campaigns. The core of the role is a shared way of working: framing commercial questions clearly, designing experiments, reasoning about cause and effect, measuring impact honestly, and explaining results to the people who act on them. You will be expected to apply this approach to whatever problems come up during the year.
You will report to a Senior Data Scientist and work with data scientists, ML engineers, and AI and data engineers who move models from research into production.
Responsibilities
Build and refine price elasticity and demand models that account for genre, format, retailer and the stage of a title's life cycle.
Plan, run and analyse pricing experiments and promotions, and report results clearly and with rigour.
When controlled experiments are not feasible, use quasi-experimental and causal methods such as matched titles, difference-in-differences or synthetic controls to estimate the effect of price changes.
Turn model outputs into pricing recommendations, then work with sales and digital colleagues to apply them and track the results.
Help develop and evaluate recommender models for automated marketing, covering feature engineering, offline evaluation and iteration.
Design and analyse campaign measurement using hold-outs, A/B tests and uplift analysis to show what a campaign actually added.
Explore, clean, transform and document the datasets behind this work, and work with data engineers on dependable pipelines.
Work with ML Engineers to move models into production, including integrations with internal services and third-party APIs.
Write well-documented, tested, maintainable code and take part in code review.
Share methods, findings and good practice with the team, and document your work so others can carry it on after your contract ends.
Requirements
Strong statistical grounding, with hands-on experience of regression, hypothesis testing and experiment design, including power analysis and the problems that arise when testing in commercial settings.
Experience estimating price elasticity, demand or sales response in a commercial setting such as retail, e-commerce or media.
Familiarity with causal inference methods for observational data.
Proficient in Python, with strong working knowledge of Pandas or Polars, NumPy, scikit-learn and statsmodels.
Strong SQL skills and comfort working with large, messy commercial datasets.
Experience with recommender systems, such as collaborative filtering, embeddings, or two-tower or similar retrieval models.
Commercially minded, focusing effort where it has the most impact on the business.
Rigorous and honest about uncertainty, willing to report null results, and clear about what the data can and cannot show.
Able to explain technical work, especially statistical results, in plain language to non-technical colleagues.
Able to understand what stakeholders need and turn it into useful analysis and data products.
Preferred: experience with Bayesian modelling in PyMC, Stan or similar.
Preferred: experience with REST APIs and with deploying or integrating models in production.
Preferred: familiarity with Git, cloud platforms (AWS preferred), and modern data tools such as Snowflake, Databricks, dbt, Dagster or similar.
Preferred: experience with AI coding assistants such as Claude Code, Cursor or GitHub Copilot.
Preferred: self-starting and quick to get up to speed, able to contribute meaningfully within a fixed-term contract.
Preferred: collaborative, shares knowledge and takes part in code review.
Preferred: reliably meets deadlines, manages priorities and time, and removes blockers.
Preferred: able to thrive in a hybrid working setup.
Preferred: an interest in books, reading and publishing is a clear advantage.
Apply with a CV and a cover letter, both as PDF, by 11:59pm on Thursday 3rd December. The cover letter must be uploaded as a separate document and should set out why you suit the role. Expect one to two pages.
Conditions
Salary is around £60,000, depending on how your skills and experience match the role, plus bonus and benefits.
The 12-month contract is fixed-term.
Hybrid working: you will be expected to work from the London office at least 1 day per week.
The company is an equal opportunities employer. Candidates with a disability who meet the essential criteria can opt in on the application form to be offered an interview, and reasonable adjustments can be requested by email.
Benefits
Bonus and benefits are included alongside the base salary of around £60,000.