Data Scientist

At Radius, we deal with a number of very large data sets, the largest of which is our detailed telemetry for the vehicles we track. These vehicles cover hundreds of millions of miles per month and we record every significant piece of driver behaviour data we can capture during those journeys, as well as recording the location, speed and heading of the vehicle at regular intervals.

This data set has created the need for new tools, practices and processes. We are making use of data science, machine learning and interactive visualisations to gather insights from this data, in order to build better products and innovate for our customers. We also use these same technologies to develop our product strategy internally. We recently presented our work on using unsupervised machine learning to process our fuel station data and to visualise our market share.

Technologies we use for our work with data include:

• Cassandra
• Apache Spark
• ActiveMQ
• Python
• Pandas
• AWS S3, Redshift, Lambda
• Tableau

Key to our success in applying these technologies to our rapidly growing, innovative organisation, are the people we employ. We are currently recruiting for data engineers and data scientists with experience of Apache Spark and ML. If you like working on challenging problems in interesting domains, with a focus on innovation, please get in touch via the details on the right.