Own the ranking strategy across Search, Homepage and Recommendations, defining how machine learning models balance relevance, personalisation, diversity, freshness and marketplace objectives.
Partner closely with ML Engineering, Applied Science and platform teams to continuously improve the quality, scalability and sophistication of our ranking systems.
Define a clear product vision and strategy for ranking, shaping how machine learning matches buyers with inventory in ways that become increasingly personal, adaptive and effective.
Partner with adjacent product and platform teams to ensure ranking capabilities are consistently applied across Search, Homepage and Recommendations.
Prioritise investments across models, features, objectives, experimentation infrastructure and technical foundations.
Use offline evaluation, online experimentation and marketplace analysis to make informed product decisions, balancing short-term performance with long-term capability building.
Drive high-quality execution
Partner with ML Engineers, Applied Scientists and Software Engineers to deliver production-quality improvements to ranking systems.
Collaborate closely with Search, Recommendations and Experience teams to ensure ranking capabilities are effectively deployed across buyer experiences.
Drive rigorous experimentation and evaluation, ensuring improvements translate into measurable gains in engagement, purchasing and marketplace outcomes.