The Applied Scientist in the MAPS POIs team contributes to the design, development, and continuous improvement of data‐driven and machine‐learning solutions that enhance the accuracy, coverage, and usability of TomTom's maps and Points of Interest products.
This role applies scientific and analytical methods to solve complex, real‐world problems at scale, translating data and models into reliable, production‐ready solutions that create value for TomTom customers and internal stakeholders.
What You'll Do
Lead the design, implementation, and integration of scalable AI/ML systems and services within the POI domain, setting direction for critical technical componentsOwn and deliver end-to-end AI/ML solutions for large-scale, high-impact initiatives, ensuring quality, scalability, and long-term maintainabilitySolve complex, ambiguous problems, defining approaches where no clear path exists and applying innovative, data-driven solutionsDesign and develop advanced,
production‐grade algorithmic solutions and ML models that address challenging real‐world use cases at scaleShape the technical architecture within your domain, making decisions that influence systems across teams and long‐term platform evolutionProactively identify risks, trade‐offs, and technical dependencies, driving alignment and resolution across stakeholdersChampion best practices and continuously raise the bar on model development, system design, and engineering excellenceProduce high‐quality, production‐level code and lead by example through thoughtful and impactful code reviewsAct as a go‐to expert within the team, providing technical leadership and guidance in your area of expertiseMentor Applied Scientists (Levels I–III), supporting their growth and strengthening the overall capability of the teamCollaborate across teams and influence Product Managers, Program Managers, and leadership on AI/ML strategy, solutions, and trade‐offs
What You'll Need
Strong, up‐to‐date expertise in Applied Science and Machi
📌 Lead Applied Scientist (Madrid)
🏢 TomTom
📍 Madrid