Lead Product Data Scientist

Job description

At Zego, we're on a mission to do the good thing, not the insurance thing.

Insurance hasn't changed much in over a century. The way we live, work and travel has. We're building the real-time, AI-driven infrastructure that powers innovative insurance, so good drivers get cover that works the way they actually drive.

For us, AI isn't a line on a roadmap or a buzzword on a slide. It's our operating reality, and it's how we build products that back drivers instead of the old insurance playbook.

Responsibilities

• Work with senior leaders to embed data science in strategy and decision making. Create and own a prioritised roadmap for where data science can have the biggest impact.
• Own Zego’s experimentation framework - design standards, power, guardrail metrics and decision rules. Coach teams to run routine experiments themselves.
• Partner with Product teams before anything is built, shaping ideas into evidence-based hypotheses and well-designed experiments. Apply causal inference where randomised tests aren’t possible.
• Build models of customer behaviour across the lifecycle - acquisition, conversion, retention, churn and lifetime value - with teams such as Marketing and Fraud.
• Use AI to scale data science across Zego, automating experiment analysis and readouts. Build self-serve tools that help teams sharpen their hypotheses.
• Take the most impactful models into production with our ML Platform team.
• Set technical direction and mentor analysts and data scientists as the capability grows.

Requirements

• Significant data science experience in a product-led business, with a track record of work that changed product or commercial decisions.
• Strong executive presence - you influence senior leaders, challenge decisions with evidence and explain results clearly to any audience.
• Expertise in experimentation and causal inference, with many online experiments designed and analysed.
• Experience building customer models such as churn, propensity, LTV or segmentation - and getting them used in real decisions.
• Strong Python and SQL, with confidence working AI-first (and the judgement to spot when AI output is wrong).
• Experience taking models into production on AWS SageMaker or a similar ML platform.
• Familiarity with experimentation or product analytics platforms such as Statsig or Amplitude.
• Experience with Snowflake, dbt and Looker or a similar modern data stack.
• Experience of marketing measurement such as media mix modelling or incrementality testing.
• A background in insurance, fintech or another regulated or subscription business.