Data Scientist

Sporting Kansas City is hiring a Data Scientist in Kansas City, KS (onsite) to build and validate predictive and decision-support models that drive football performance insights.

Responsibilities

• Partner with coaches, analysts, scouts, and other stakeholders to identify football questions and convert them into advanced modelling projects
• Build strong relationships across the Data and Analytics team to ensure alignment with Club and department strategy
• Work closely with the First Team Data Engineer to ensure models are supported by reliable data and production-ready workflows
• Collaborate with the First Team Data Analyst to translate model outputs into clear, actionable insights
• Support cross-Club collaboration and communication as needed, championing adoption of advanced analytics across Sporting Kansas City
• Lead end-to-end development of applied advanced modelling projects, from problem definition through deployment and review cycles
• Create tools and best practices for experimentation, including testing, validation, versioning, monitoring, model governance, and documentation
• Continuously assess model performance and incorporate stakeholder feedback to maintain reliability and flexibility as the Club evolves
• Evaluate emerging methods and research to keep Sporting Kansas City current with data science best practices and trends
• Develop advanced models for medical, sports sciences, scouting, coaching, and performance analysis workflows
• Build advanced football metrics for player, team, league, and valuation models using multiple data sources
• Develop advanced metrics using event, tracking, and physical data
• Support predictive modelling for load monitoring and management, player availability, injury risk, and other key initiatives in collaboration with medical and physical performance staff
• In alignment with wider Data and Analytics teams, support forecasting and scenario-analysis tools for squad and salary cap planning
• Challenge existing data, systems, and practices to drive innovation
• Work with the First Team Data Engineer to productionize models and implement ML projects seamlessly

Requirements

• Bachelor's degree in computer science, data science, or a related STEM subject
• Experience in a Data Science, Machine Learning, Applied Statistics, or similar role
• Proven experience designing, validating, and monitoring applied machine learning models
• Robust experience using SQL and Python for data analysis, modelling, and automation
• Strong understanding of statistical modelling, experimental design, and model evaluation
• Creative and curious problem solver with a positive attitude to new challenges
• Proactive and able to learn new skills, working effectively as part of a team
• Excellent attention to detail and evidence of developing strong analytical skills
• Excellent communication skills, with ability to translate technical concepts into practical solutions

Technologies

• SQL
• Python
• Tableau

Preferred Experience

• Prior experience working within an elite soccer club or high-performance sporting environment
• Experience working with soccer event, tracking, and physical performance datasets
• Experience developing models for elite athlete recruitment, physical performance, squad planning, player availability, and load and fatigue management
• Experience deploying machine learning models and working with cloud-based environments
• Strong understanding of technical and tactical aspects of soccer
• Evidence of experience working in the MLS
• Experience using data visualization tools such as Tableau or equivalent software

Physical Requirements

• Ability to work in office, stadium, and outdoor environments, with travel as required
• Ability to occasionally lift up to 25 pounds
• Ability to work non-traditional hours, including evenings, weekends, and holidays

Additional Responsibilities

• Represent Sporting Kansas City professionally at all times
• Maintain confidentiality of sensitive information
• Comply with Club policies and procedures
• Perform other duties as assigned