Lead Data Scientist - Nike Sports Research Lab - Nike Innovation

Provides hands-on technical leadership for complex projects that use sensor and camera data to understand human movement and performance. It partners with researchers in biomechanics, physiology, perception, and related disciplines, along with data scientists, engineers, product managers, and other innovation partners. It reports to the Director of Data Science and provides technical leadership within multidisciplinary project teams, focusing on technical execution, project coherence, and mentorship rather than organisation-wide data science strategy.

• Provide hands-on technical leadership for complex projects that use sensor and camera data to understand human movement and performance.
• Develop rigorous analytical solutions, guide project execution, and work closely with scientific and engineering partners to deliver credible, useful, and reusable outcomes.
• Apply machine learning, computer vision, signal processing, statistical modelling, and related methods to problems in human movement and athletic performance.
• Develop analytical workflows using data from IMUs, wearable sensors, camera-based systems, computer vision pipelines, and other measurement technologies.
• Connect algorithm outputs to the movement or performance phenomena they represent, making assumptions, limitations, uncertainty, and failure modes explicit.
• Lead the technical execution of complex projects by clarifying questions, defining analytical plans, coordinating contributions, and communicating risks and trade-offs.
• Design and evaluate models and measurement approaches using appropriate scientific, statistical, and computational validation methods.
• Build reusable datasets, software, pipelines, and documentation that support reproducible research and future project work.
• Investigate and evaluate emerging methods, technologies, and state-of-the-art research, translating promising advances into practical, scientifically credible capabilities for athlete measurement and performance analysis.
• Provide technical guidance, code and analysis review, and mentorship while communicating methods and findings clearly to technical and non-technical partners.

• Master's degree in Computer Science, Data Science, Statistics, Engineering, Biomechanics, Kinesiology, Applied Mathematics, Physics, or a related field; any suitable combination of education, experience, and training will be accepted.
• 6+ years of relevant applied experience post-degree in data science, machine learning, statistical modelling, signal processing, computer vision, or a related technical field, including ownership of complex projects.
• Strong Python proficiency and experience building tested, maintainable, reproducible analytical software using modern version control, code review, and development practices.
• Experience working with complex measurement data, such as time-series signals, IMUs, wearable sensors, image or video data, camera-based systems, or multimodal datasets, with rigorous signal processing and computer vision model evaluation and validation.
• Strong communication and collaboration skills.
• Ability to independently solve difficult technical problems, guide project-level decisions, and help other contributors deliver high-quality work.
• Ability to work with ambiguous research and innovation questions, translate them into rigorous analytical plans, and collaborate across scientific and technical disciplines.
• Ability to remain hands-on in analysis and software development while communicating assumptions, limitations, trade-offs, and findings clearly.
• Understanding that sensing and machine-learning systems are only useful when their outputs can be connected to the physical and scientific realities they are intended to represent.
• Strong algorithmic skills combined with practical project leadership and genuine curiosity about human movement and performance.

• Experience with human movement, biomechanics, physiology, sport science, pose estimation, sensor fusion, and cloud data platforms is strongly preferred.