Are you looking for a role where you can lead adata science team, work on real world forecasting, pricing and logistic problems and work with beautifully granular datasets that are improving the lives of millions of people every day?

We are looking for a Lead Data Scientist to join our data science team in theTesco Supply Chain Transformation team.

We can offer flexible working and are flexible on location. You will be able to team up with a senior back end developer and help shape hypothesis, explore minimum viable products, and scale the product using our Hadoop architecture.

As a Data Scientist, you will have the following responsibilities:

• Lead the conversations with main stakeholders to define the problems that can be solved through Data Science and Machine Learning.
• Own an end to end vision of the data products that will be launched and be the main contributor of the key parts that will make the product successful.
• Encourage other members of the team to use best practices when adding new features, correcting for outliers or choosing a specific KPI to measure performance.
• Build fast prototypes that solve 80% of a problem, while having a full understanding of the challenges ahead gained through experience in other projects.
• Collaborate with a senior backend engineer to define the proposed data architecture in a Hadoop environment.
• Measure the real performance improvements of your data products.
• Share your findings with the rest of Tesco and explore new technologies.

• A solid statistical background including probability and set theory, time series analysis, A/B testing.
• Experience applying machine learning models in real world big data environments (Terabytes) and can foresee the challenges and opportunities of choosing different approaches to solve a problem.
• A deep understanding of at least one machine learning algorithm.
• Productised classification, clustering and/or regression algorithms, and have a good understanding of most of them.
• Experience building or helping to build processes that reduce the maintenance costs / technical debt associated to new data products.

• Experience working with pandas, have built data products using tensorflow or scikit-learn and have most likely spent over 1000 hours coding in python.
• Able to inspire a team member to reduce 100 lines SQL query into a more simple python function.
• Experience working or would like to explore working with Docker and understand when to git push and when to git commit.
• Built or tried to build a data product on your own or with a very small team as a side project.

• You prefer to spend multiple days working on your own on a data problem and work mostly asynchronously with other team members.
• Able to think of the best features you would like to use and at the same time understand what could be value / effort relationship of having or not having them.

Agile problem solver

• You have learned the value of moving from a proof of concept to minimum viable products to full products, and can review the data product at different stages to continue, re-think or stop the project.