Senior Data Scientist - Creative Optimization London, England

Choreograph is WPP’s global data products and technology company. We’re on a mission to transform marketing by building the fastest, most connected data platform that bridges marketing strategy to scaled activation. We work with agencies and clients to transform the value of data by bringing together technology, data and analytics capabilities. We deliver this through the Open Media Studio, an AI-enabled media and data platform for the next era of advertising. We’re endlessly curious. Our team of thinkers, builders, creators and problem solvers are over 1,000 strong, across 20 markets around the world.

The Creative Optimisation product is a DCO (Dynamic Creative Optimization) application that is built and maintained in-house at Choreograph, by the Optimisation team. The product enables personalisation of creative content at scale, across multiple channels such as digital display, mobile apps, CTV, YouTube, video and social. This is no start-up. The application is already serving tens of millions of ads and terabytes’ worth of media, every day in real-time, across the globe.

We are on the lookout for a Senior Data Scientist to join our team to co-develop a step-change feature: Algorithmic Content Optimization (ACO). Our vision is to leverage data signals to algorithmically serve the most relevant creative to the right audience in the right moment that maximises performance, continuously. The role will report to VP Data Science, and be part of a small (but growing!) team of Data Scientists.

The ideal candidate will have a background in Reinforcement Learning (or related disciplines), with hands-on cloud technology experience. Whilst commercial experience is highly desirable, given the deployment of RL at scale remains relatively nascent, we’re happy to consider candidates with academic research as well as commercial background. The candidate though does have to be truly, technically competent. For the scale and complexity at which our product operates, off-the-shelf solutions are often not fit-for-purpose. The ideal candidate has to have the ability to customise source code, add in new features and code from scratch. Whilst model deployment/software development experience is highly desirable, we do have a team of engineers to support so exposure in this space will be sufficient.

Culture-wise, we’re looking for a great team player who is passionate about applying Data Science techniques to solve complex problems and drive innovation. In return, you will get the opportunity to solve cutting-edge problems, and drive measurable performance improvement for our clients. Not to mention, working with a team of supportive, seasoned developers, product managers and data scientists who have successfully built and deployed scalable, global products.

Key Responsibilities:

• Develop and optimize the ACO algorithm(s) and related Data Science components for the product.
• Design and contribute to the end-to-end machine learning pipeline from data collection, reprocessing to model training, simulation, evaluation, deployment and experimentation/testing.
• Implement and interpret explainability frameworks to provide clear insights into model decisions, ensuring transparency and compliance with WPP standards.
• Collaborate with stakeholders to identify business needs and translate these requirements into technical solutions that are scalable and impactful.
• Conduct rigorous model testing and validation to ensure robustness and accuracy.
• Prepare detailed documentation and reports that communicate complex model behaviours, predictions, and insights in a manner accessible to both technical and non-technical audiences.
• Stay abreast of academic research and industry advancements in RL, plus AI/ML in general.
• Knowledge-share and support the wider team and Data Science community to drive innovations based on your work.

Essential qualifications:

• Bachelor's or master's degree in Data Science, Computer Science, Engineering, Statistics, or a related quantitative field.
• Hands-on (academic/commercial) experience in implementing Reinforcement Learning (or a related discipline).
• Proficiency in Python and SQL.
• Experience of using Cloud technologies. GCP will be ideal, but other mainstream ones are fine as well.
• Experience of/exposure to model deployment and/or software development.
• Demonstrable statistical and machine learning knowledge.
• Effective communication skills to work with different stakeholders/team members with varying degrees of knowledge in Data Science.
• A collaborative team player.

Highly Desirable qualifications:

• Research degree (MRes or PhD) with a thesis on Reinforcement Learning or related discipline.
• Knowledge/experience in Causal Inference.
• Commercial experience in implementing and deploying RL or a similar personalisation system.
• Commercial experience in software development.
• Commercial ML Ops experience.

(Please note this is a UK based role and requires individuals to have the right to work in this location.)