Description
You're a data scientist with broad quantitative skills and a background in microeconomics, econometrics, or finance. You'll own data science work across Qogita's business — from forecasting and classification through to experimentation and recommendation systems — and act as the team's go-to on how prices are set, how buyers respond, and how market structure shapes commercial decisions. The Data Science team works cross-functionally with Product, Finance, and Commercial teams to build the analytical and modelling layer that drives Qogita's wholesale marketplace.
You're a data scientist with broad quantitative skills and a background in microeconomics, econometrics, or finance. You'll own data science work across Qogita's business — from forecasting and classification through to experimentation and recommendation systems — and act as the team's go-to on how prices are set, how buyers respond, and how market structure shapes commercial decisions. The Data Science team works cross-functionally with Product, Finance, and Commercial teams to build the analytical and modelling layer that drives Qogita's wholesale marketplace.
Requirements
- Build and deliver data science solutions across the stack — predictive models, segmentation, forecasting, ranking systems, and pricing models — depending on where the business need is greatest
- Act as the team's domain expert on pricing and market economics: take ownership of the modelling approach, analytical strategy, and how findings translate into commercial recommendations
- Research, build, deploy and maintain predictive and analytical models that reflect B2B buyer behaviour and wholesale market dynamics
- Design and analyse experiments and A/B tests, owning statistical validity and translating results into recommendations Product and Commercial can act on
- Apply a range of quantitative methods — regression modelling, causal inference, ML techniques — to business problems across pricing, demand, market liquidity and beyond
- Collaborate with Engineers to ship models via reproducible MLOps workflows, including experiment tracking, model serving, and production monitoring
- Communicate findings and model limitations clearly to Finance, Commercial, and Product stakeholders
