Zoopla

Join Zoopla, and help us reimagine the property industry!

Our vision is to digitise the entire home owning and buying experience.

Over the past two years, we’ve doubled our team and began to create a new suite of products that are already delivering results for our estate agents.

Our salaries and bonuses are competitive, and our exceptional employee benefits are rated 4.4/5 on review sites.

We are looking for a Senior Data Scientist to primarily support our AVM project. Hometrack is a leading provider of residential property market intelligence and valuation data and is a Product and Technology function of Zoopla. Founded in 1999, they are trusted by major mortgage lenders, house builders and government bodies as a source of fast, accurate and precise property information.

Since launching their automated valuation model (AVM) in 2002, they have grown to be the market leader in AVM technology and now provide over 85 million automated valuations each year to lenders, investors, advisers, developers, housing associations and people, helping them decide where to invest and develop, what to lend on, how to optimise assets and helping to improve understanding on what a home is worth.

Hometrack’s clients account for 75% of the UK mortgage market. In 2017, Hometrack was acquired by Zoopla Property Group.

The role

You will be responsible for maintaining and improving the industry leading Hometrack AVM (Automated Valuation Model to estimate the value of residential properties) and other statistical models and data systems related to it. We are always looking to innovate and better identify and understand what data makes a difference to property value and how to incorporate this into our models and products.

Today our areas of focus include climate change and the risks it poses to UK property and their values, and predicting how property prices may change in the future. We continue to assess and embed advanced machine learning and AI into our solution and are looking for a scientist to join our team and contribute to these developments. This is a fantastic opportunity to join a team positioned at the heart of a hugely ambitious and highly regarded company in prop tech.

What will you be doing?

• Being responsible for the performance of our live models. Automating continual retraining and accuracy testing. Detecting model drift and deploying model improvements to ensure the reliability of our valuations for lender clients.
• Researching new datasets and advanced machine learning techniques that can be used to increase the accuracy of our property valuation model and improve our AI capabilities across our model and product range
• Design and create the pipelines and infrastructure to deploy data science models at scale
• Create the tools, frameworks and libraries that will enable the acceleration of our Data Science product delivery and spread the best ML Ops standards across the whole business
• Work collaboratively with fellow data scientists, client analysts and data engineers
• Meeting with stakeholders to translate business needs into data science problem

Requirements

• Passion for Data Science and drive to know new technologies and techniques
• Strong statistical and mathematical skills
• Fluent in Python (essential)
• Knowledge of ML packages such as NumPy, SciPy, Scikit-Learn, Pandas, Keras, TensorFlow, PyTorch, PySpark
• Hands-on experience in implementing a ML model from end to end in business environment
• Ability to apply advanced solutions to drive business improvements
• Independent, solution oriented and highly motivated individual
• Demonstrable commercial experience (product and tech company is a plus)

If you don’t have experience working as a Data Scientist, but you have a passion for it and you are an experienced developer or a data analyst, apply!

Benefits

We are looking for someone with:

• An advanced degree in Computer Science, Mathematics, Physics or other quantitative discipline
• Strong Python experience and knowledge, with the ability to write stable, scalable and maintainable code
• You worked in an R&D environment and/or you are intimately familiar with the fundamentals of the scientific research method: critical thinking, formulating hypotheses, running experiments, drawing conclusions etc.
• Experienced at identifying problems that can be solved with machine learning and delivering them from prototype through to production
• Strong understanding of machine learning applications, development life cycle processes and tools: CI/CD, version control (git), testing frameworks, MLOps
• Comfortable working with Docker and containerised applications
• Experience with data science Python libraries such as Scikit-learn, Pandas, NumPy, Tensorflow etc.
• Experience using AWS or similar cloud computing platform
• Great communicator - convey complex ideas and solutions in clear, precise and accessible ways
• Team player who cares about accelerating not only Zoopla’s technical capabilities, but also empowering colleagues