Our client is building a mobile application for a major football club, designed to deepen fan engagement, optimize monetization, and deliver a seamless experience both inside the stadium and remotely. The ambition is to be an industry leader in technical capability and user interaction.

Your part is the cloud data architecture and the machine learning behind it: a scalable AWS infrastructure supporting millions of concurrent users, integrated with existing systems such as Ticketmaster and VenueNext, feeding ML models that personalize what every fan sees.

The architecture also has to hold up to WCAG, GDPR, and CCPA requirements with strong security protocols throughout.

• Data architecture: develop and maintain scalable cloud data architecture on AWS — Glue, Lambda, S3, and Redshift
• Pipelines: implement ETL processes and real-time data pipelines for efficient data handling and integration across the stack
• ML development: build, train, and deploy models with SageMaker, scikit-learn, XGBoost, and TensorFlow to personalize the app experience
• ML operations: manage ML pipelines and maintain a model registry for version control and clean deployment
• Automation & monitoring: orchestrate workflows with AWS Step Functions and CloudWatch, and run CI/CD through CodePipeline and CodeBuild
• Infrastructure & security: provision cloud infrastructure with Terraform, apply IAM best practices, and use Docker for consistent environments
• Collaboration: work with UI/UX designers and developers to integrate data-driven features, and turn analysis into actionable insight

• Strong Python and SQL for building scalable data solutions
• Extensive AWS experience across data integration, machine learning, and infrastructure management
• Production ML expertise — practical experience deploying and maintaining models, not just training them
• CI/CD practices and the tooling to automate development and deployment
• Infrastructure as code with Terraform, and containerization with Docker
• Compliance awareness: WCAG, GDPR, and CCPA requirements in a consumer-facing product
• Cross-functional collaboration — you can translate business needs into technical solutions and explain the result

• A consumer product at real scale — millions of concurrent users, live event traffic peaks
• Full ownership of the data and ML layer, from architecture to production monitoring
• A team that expects professional delivery, detail orientation, and proactive communication
• A "can do" culture where feedback is given and received constructively
• Fully remote work with a US-overlapping rhythm

ASAP