Senior Data Scientist

Company overview

Annual releases gave way to two-week sprints years ago, and the platform now handles over 200 million API calls a day. We started in 1992 and have grown to about 4,100 people. We keep recurring meetings to Tuesdays and Thursdays where we can.

The position

This is a backfill for a team member who is relocating. The operations team works directly with product and finance. You'll design experiments, build forecasts and explain the results. We work hybrid out of Newcastle upon Tyne, usually three days in, two days remote.

What you'll do

• Translate vague business questions into problems the data can actually answer.
• Pull and shape data with SQL from Snowflake, BigQuery or Databricks.
• Build predictive models in Python using scikit-learn, XGBoost or LightGBM.
• Estimate causal effects with difference-in-differences, propensity matching or regression discontinuity.
• Work with ML engineers to move models into production and monitor drift.
• Design and analyse A/B tests, including power calculations and guardrail metrics.
• Segment customers and build churn and lifetime value models.

Required qualifications

• 5+ years of applied data science experience.
• Ability to communicate uncertainty and tradeoffs to non-technical audiences.
• Experience building and validating machine learning models on real business data.
• Data visualization in matplotlib, seaborn, Plotly or a BI tool.
• Strong Python (pandas, NumPy, scikit-learn) and SQL.

Also helpful

• MLflow or another experiment tracking tool.

What you get

• Private medical insurance.
• Workplace pension.
• 28 days annual leave including bank holidays.
• Life assurance (4x salary)

We are an equal opportunities employer and welcome applications from all suitably qualified persons.

Successful applicants will be contacted within a week of the closing date.

Unfortunately we cannot offer visa sponsorship for this role.

Start: Flexible.

Demo job created on 11jobs for testing and demonstrations. It is not an actual opening at Canopycast.