This job post is closed and the position is probably filled. Please do not apply.
🤖 Automatically closed by a robot after apply link
was detected as broken.
Description:
The role involves analysing large volumes of customer data from various sources, such as fuel purchases, convenience store transactions, car services, and EV charging, to uncover actionable business insights.
The candidate will be responsible for cleaning, pre-processing, and transforming raw data into structured formats suitable for analysis using SQL and Python.
The position requires the development, tuning, and validation of machine learning models to predict customer behaviour, with the goal of optimising marketing strategies and improving customer retention.
The Data Scientist will design and create compelling data visualisations to effectively communicate findings to stakeholders.
The role includes responding to and solving ad-hoc business questions by extracting and analysing relevant data, providing timely and accurate insights.
The candidate will employ deterministic record linking techniques, such as blocking, fingerprinting, aggregation, normalisation, and similarity measures, to accurately match and merge customer records.
The position involves working collaboratively with cross-functional teams, including technology (data engineers, analysts, and architecture) and business (marketing, operations) to implement data-driven insights into business processes.
The Data Scientist will use AWS services like Redshift and Athena to manage and analyse large datasets efficiently in a cloud environment.
The role requires developing and presenting data stories that translate complex analytical results into understandable and actionable insights for non-technical stakeholders.
Requirements:
The candidate must have experience working with SQL, Python, Git, and AWS services, specifically Amazon Redshift and Athena.
Proficiency in using Jupyter Notebook and Visual Studio Code, which is the client’s recommended IDE, is required.
The applicant should have experience with deterministic record linking techniques and machine learning model development.
Good coding best practices are essential for this position.
It is considered a plus if the candidate has experience with Amazon SageMaker, PySpark, and MLOps, although these are not essential.
Benefits:
The position offers the flexibility of remote work, allowing employees to work from anywhere.
The role is a contract position, providing opportunities for project-based work with global clients and big-name brands.
Working with a small, dynamic team that combines design thinking with data science to solve complex business problems.
The opportunity to contribute to a growth journey within a professional services firm, enhancing skills and experience in data science and analytics.