Data Pipelines & ETL

A key part of this role is understanding how data moves through the organisation and being able to troubleshoot issues when things go wrong.

You'll be expected to:

• Work hands-on with ETL (Extract, Transform, Load) processes and data pipelines.
• Extract and transform data from multiple sources for analytics and machine learning purposes.
• Investigate and resolve pipeline failures, data-feed issues and tracking gaps.
• Identify how upstream data-quality issues affect reporting and production models.
• Work with Engineering and other technical teams to resolve data issues.
• Validate data used by production models and reporting.
• Maintain reliable, repeatable data processes with appropriate monitoring and documentation.

Data Science & Machine Learning

• Maintain the existing suite of production ML models, including scheduled refreshes, retraining and redeployment.
• Monitor model performance and identify potential model drift or degradation.
• Troubleshoot issues affecting model inputs, pipelines and outputs.
• Perform data-quality checks on model inputs and production pipelines.
• Support partner-ranking changes and credit-model requirements in Canada.
• Ensure models and associated processes remain reliable without unnecessarily rebuilding them from scratch.
• Document and hand over models, pipelines, monitoring and reporting to the permanent team at the end of the contract.

What we're looking for

We're looking for an experienced hands-on Data Scientist who can operate independently in a production environment.

Essential

• 5+ years' experience in Data Science and/or advanced analytics.
• Proven experience working with production machine-learning models.
• Hands-on experience maintaining, monitoring, refreshing and troubleshooting existing ML models.
• Strong Python and SQL skills.
• Strong understanding of ETL, data pipelines and data transformation.
• Experience troubleshooting pipeline failures, data feeds and data-quality issues.
• Comfortable working with existing codebases and production environments rather than only building new solutions.
• Experience with model performance monitoring and/or model drift.
• Strong understanding of data quality and its impact on analytics and ML.
• Ability to take ownership of BAU processes with minimal supervision.
• Excellent communication skills, with the ability to explain technical issues clearly to business stakeholders.
• Comfortable working across Product, Engineering, Marketing, Compliance and Commercial teams.
• Degree or equivalent experience in Data Science, Computer Science, Mathematics, Statistics, Physics or another quantitative discipline.

Desirable

• Experience within financial services, fintech, credit, insurance or another regulated environment.
• Experience with FCA or other regulatory reporting.
• Experience working with revenue, customer, partner or commercial analytics.
• Contract or consulting experience working to fixed deadlines.
• Experience using AI tools such as Claude Code, OpenAI or similar to improve productivity and automate day-to-day workflows.
• Familiarity with agentic AI workflows.

This role will suit someone who enjoys owning problems end-to-end.

You'll need to be comfortable receiving an issue such as:

"Revenue has dropped unexpectedly — is this a genuine business movement or a data problem?"

and working through the data, pipelines, models and stakeholders to establish what's happening and provide an answer.

You won't have a large team of people underneath you to do the investigation. You'll be expected to get into the data yourself, troubleshoot issues and keep the operation moving.

If you enjoy being the person who understands how the data works, spots when something isn't right and can fix it, this could be a very good fit.

If you're an experienced Senior Data Scientist with strong Python, SQL, ETL/data pipeline and production ML experience, we'd be keen to hear from you.