York, Yorkshire London North Eastern Railway

Why LNER?

We go beyond. For everyone. Our vision is to be the most loved, progressive and responsible way to travel for generations to come. Now we're looking for the people who can deliver this, every day.

Since we took over on the East Coast mainline, we've been changing the face of rail travel. Our new Azuma train has brought faster journey times, more space and greater reliability. Our exciting plans to embrace new ideas, experiences, backgrounds and ambitions make this the ideal time to join.

Bringing passion. Being bold. Always caring. Owning it. They're the values that make us LNER.

What you will be doing:

We have an exciting opportunity for a Data Scientist to join our newly formed Machine Learning team within our Digital and Innovation department on a permanent basis (with the potential for further fixed term opportunities).

We're driving a lot of innovation related to Machine Learning and AI in the rail industry and the scope of possibilities is growing rapidly. The Machine Learning team is developing predictive solutions to support decision making across multiple teams in the company. We also work with teams across the company to increase data literacy and help teams see where Machine Learning and AI can integrate into their solutions, ease and improve decision making thus making the work more enjoyable and creative.

Our Data Scientist role forms an essential part of LNER's Machine Learning team, primarily by building statistical models to enable the benefits of business-challenge led use cases to be sought after and then realised.

This role will also involve:

1. Supporting the end-to-end business-challenge led process from feasibility testing an idea at conception, to testing at a proof of concept phase to realising the benefits at production and BAU maintenance. This will be done by taking a key role in the 'scrum team' as the data science expert, collaborating with Machine Learning Product Managers and Machine Learning Engineers to collectively be responsible for successful delivery of capabilities.
2. Being responsible for building machine learning models that meet the requirements of a business challenge or opportunity, including selecting which model is best for each unique project and seeing this through to model delivery and testing.
3. Supporting the Machine Learning Technical Lead by implementing best practices for code development, training and testing models, deployment, ethics, and approach to productionising solutions.
4. Being a subject matter expert in data science theory and practice, to support the Machine Learning team to demonstrate to the business how data science solutions could benefit their areas.
5. Critically assessing and validating all modelling related tasks in machine learning production pipeline.
6. Designing, building, and implementing the quality assurance safeguards for machine learning production pipeline.
7. Ensuring the high-quality documentation of the machine learning pipelines.
8. Hybrid working with Tuesdays and Thursdays based in either our York or Kings Cross office.

What you'll need:

We are looking for someone who has proven experience in a Data Scientist role working on a wide variety of projects, within an in-house function. You'll also have:

1. Experience of taking on novel, business-challenge led problems, developing algorithms iteratively and implementing productionised operational solutions to drive the benefit of machine learning.
2. Knowledge of best practices for statistical data modelling, analysis and exploration, machine learning.
3. Fluent in writing well-structured Python code for machine learning algorithms.
4. An excellent knowledge of basic machine learning libraries, such as NumPy, SciPy, Pandas, Dask, PyTorch, Tensorflow, etc.
5. A solid grasp of standard data science techniques, for example, supervised/unsupervised machine learning, model cross validation, Bayesian inference.
6. Experience in working with large amounts of raw data; preparing, cleansing and processing.
7. An understanding of coding best practices and experience with code and data versioning (using Git/CodeCommit), code quality and optimisation, error handling, logging, monitoring, validation and alerting.
8. A 'test and learn' approach mentality.
9. Experience in working with AWS Machine Learning Stack i.e. Sagemaker Studio (desirable).
10. Familiarity with Tableau and/or other visualisation tools (e.g. Power BI) (desirable).
11. Strong stakeholder management, communication, and engagement skills tailored to the audience (exec team, senior stakeholders, data engineers) (desirable).

If this sounds like you, what are you waiting for?

Apply now!