Data Science Team Leader in London

As the Senior Team Lead for Data Science – Courier Pay & Incentives, you will be the strategic leader responsible for maximising the impact of our real‑time courier incentive systems on supply quality, earnings fairness, and operational efficiency across our global delivery network. This is a high‑impact, real‑time‑first leadership role. Courier pay and incentive systems operate under strict latency and fairness constraints — decisions made in milliseconds affect earnings for hundreds of thousands of couriers and directly shape supply availability at the moment demand arrives. Your team sits at the intersection of economics, real‑time ML, and logistics operations.

You will own the data science strategy for courier compensation models, dynamic boost and surge mechanisms, engagement incentives, and the behavioural analytics that underpin fair and effective pay design. Experience in real‑time systems, experimentation at scale, and economic modelling is essential for providing credible technical leadership to a senior team of Data Scientists.

Location: Hybrid – 3 days a week from our London, Berlin or Amsterdam office & 2 days working from home. Reporting to: Head of Data & Analytics.

• Team Leadership & People Management: Lead, manage, and develop a high‑performing team of Data Scientists through mentorship, coaching, and rigorous performance management. Build a culture that prizes speed, rigour, and courier‑centric thinking.
• Own the Real‑Time Pay & Incentives Roadmap: Define and drive the data science strategy for real‑time courier pay systems – including dynamic earnings floors, surge and boost mechanisms, per‑order pay calibration, and engagement‑based incentive programmes. Partner closely with Product Management and Operations to align priorities with supply health and commercial objectives.
• Drive Business Impact: Take ownership of key courier supply KPIs – availability, acceptance rates, session duration, and earnings competitiveness. Ensure the team focuses relentlessly on the highest‑leverage interventions and that modelling decisions are grounded in empirical evidence and causal reasoning.
• Business Root Cause Analysis (RCA) & Solution Strategy: Lead deep diagnostic analyses of supply shortfalls, incentive inefficiency, and courier churn. Identify whether issues are structural (pay levels), temporal (real‑time allocation), or behavioural (engagement and activation patterns), and translate findings into concrete modelling strategies.
• Stakeholder Communication: Act as the primary interface between the Data Science team and senior stakeholders across Product, Operations, Finance, and Legal. Translate complex economic models and real‑time system behaviour into clear, actionable business narratives.

• Real‑Time Incentive Engine Architecture: Define the conceptual design and validation approach for real‑time pay and boost models that must make decisions within tight latency budgets. Balance model sophistication against inference speed, reliability, and fairness constraints.
• Dynamic Pricing & Surge Modelling: Oversee the development of models that predict local supply‑demand imbalances and compute optimal real‑time boost levels. This includes zone‑level supply forecasting, elasticity estimation, and incentive spend efficiency optimisation.
• Fairness, Consistency & Earnings Transparency: Ensure pay models are auditable, consistent, and free from unintended biases. Define monitoring frameworks that catch real‑time drift in earnings distributions, acceptance behaviour, and incentive take‑up rates before they affect supply or courier trust.
• Technical Guidance & Design Review: Serve as the senior technical expert guiding architectural decisions for pay and incentive models. Maintain high standards through rigorous design discussions, experiment reviews, and model evaluations.
• MLE Partnership: Collaborate closely with Machine Learning Engineers who own deployment and scaling. Ensure models are transitioned with robust documentation, clear latency and throughput requirements, and production‑ready validation pipelines.

• Causal Experimentation at Scale: Lead the design and execution of experiments to measure the true causal impact of pay changes, new incentive structures, and engagement campaigns – accounting for marketplace interference, SUTVA violations, and geo‑based spillovers.
• Courier Behavioural Modelling: Direct the team's development of supply elasticity models, courier lifecycle and churn prediction, session‑level engagement models, and earnings perception analytics. These models directly inform how incentives are personalised and timed.
• Incentive ROI & Spend Optimisation: Build frameworks for measuring incentive efficiency – balancing the short‑term supply response against long‑term courier retention and total incentive spend. Guide the team towards optimisation strategies that maximise per‑pound‑spent supply impact.
• Insight Generation: Guide the team in synthesising large‑scale geospatial and temporal courier data – GPS traces, session events, earnings logs, and order outcomes – into actionable modelling and policy recommendations.

• Proven, extensive experience in leadership and people management, with a demonstrated ability to mentor and develop senior Data Scientists in a fast‑moving product environment.
• Prior hands‑on experience building and deploying ML models in production, ideally within real‑time or low‑latency systems. This background is essential for providing credible strategic and architectural guidance.
• Strong conceptual grounding in incentive design, dynamic pricing, or labour economics – with the ability to reason about behavioural responses, market equilibria, and fairness trade‑offs in complex two‑sided systems. Experience with sequential decision‑making systems is considered a plus.
• Deep expertise in causal inference and experimentation methodology – A/B testing, switchback experiments, difference‑in‑differences, and interference‑aware designs for marketplace settings.
• Demonstrated ability to diagnose production model performance issues – particularly in real‑time systems where feedback loops, distribution shift, and latency constraints interact.
• Experience with geospatial analysis and time‑series modelling is strongly preferred, given the zone‑level, time‑sensitive nature of supply and demand dynamics in on‑demand logistics.
• Exceptional communication and stakeholder management skills, with the ability to influence both technical peers and non‑technical business leaders on decisions involving significant financial and operational trade‑offs.