We are seeking a technical and hands-on Data Scientist to drive the evolution of our analytics capabilities. Moving beyond traditional reporting, you will be responsible for building reproducible, code-first data products that power our internal decision-making and customer-facing features.
You will play a central role in our transition to an Azure-native stack, utilising Python, Spark, and Cloud computing to automate complex workflows. You will champion a culture of reproducibility and engineering rigour, moving us away from manual ad-hoc analysis towards robust, scalable data science solutions.
Key Responsibilities
* Advanced Analytics & Modelling: Design and implement predictive models and algorithms that unlock new value from our vehicle telemetry data.
* Code-First Automation: Replace manual Excel/VBA workflows with robust, automated Python pipelines. You will be responsible for "productionising" insights to ensure they run reliably without manual intervention.
* Cloud & Big Data: Utilise Spark and Azure (Databricks/Synapse) to process large datasets efficiently. You will work extensively with Notebooks for both exploration and deploying production jobs.
* Reproducibility & Governance: Champion software engineering best practices within the data team, including version control (Git), code reviews, and defensive coding to ensure all analysis is reproducible and audit-proof.
* Data Storytelling: Translate complex datasets into clear, interactive narratives that drive strategic action across the Engineering and Development teams.
* Python Expertise: Expert proficiency in Python for data manipulation and automation is essential. You must be comfortable writing production-grade code, not just scripts.
* SQL Mastery: Advanced SQL skills for querying and transforming data from disparate sources.
* Big Data Frameworks: Hands-on experience with Spark (PySpark) or similar and working within distributed computing environments.
* Cloud Computing: Familiarity with cloud platforms, preferably Azure (Data Lake, Databricks, Data Factory).
* Notebooks & IDEs: Experience using Jupyter/Databricks Notebooks for analysis and VS Code for pipeline development.
* CI/CD & Version Control: Experience working in an agile environment using Git for version control to manage codebases and collaborative workflows.
Personal Characteristics
* An active problem solver who hates manual repetition and constantly looks for ways to automate processes.
* Focussed on continuous development: You stay up to date with the latest libraries, tools, and cloud trends.
* A confident communicator who can explain complex machine learning concepts to non-technical stakeholders.
* Personable and outgoing, with a good sense of humour.
This is a full-time role (37.5 hours per week) operating on a hybrid basis, with office days on Tuesday and Wednesday.
We believe great work deserves great support. Alongside a competitive package, we offer a range of benefits designed to reward our colleagues:
* 25 days’ annual leave
* Christmas closure
* A day off to celebrate your birthday
* Life assurance
* Health and dental cash plans
…and much more. Visit the "Our Benefits" section of our website to discover the full range of benefits available to our team.
#J-18808-Ljbffr