Data Science Lead, Flo

• 7+ years applied ML experience building and deploying models in production
• 4+ years managing technical teams (ML engineers, data scientists, or similar)
• Expert knowledge of ML fundamentals: supervised/unsupervised learning, time series, causal inference
• Experience with modern ML frameworks (PyTorch, TensorFlow, scikit-learn, CatBoost)
• Experience with growth analytics, attribution modeling, or marketing effectiveness
• Understanding of user acquisition funnels and retention optimization
• Comfortable translating business requirements into technical roadmaps
• Strong communication skills - can explain complex models to executive stakeholders
• Experience deploying ML models at scale (millions+ predictions/day)
• Knowledge of MLOps practices: model versioning, monitoring, automated retraining
• Understanding of data engineering fundamentals and cloud platforms

Desirable

• We're hiring a Data Science Lead in London to build and lead our Predictive Growth Optimization team – pioneering ML models that power our user acquisition strategy, predict lifetime value, and optimise our $25M+ annual marketing spend across channels
• This role owns the strategy, development, and continuous improvement of Flo's pLTV system - a mission-critical model reused across UA, AdTech, personalization, and financial forecasting
• You'll balance hands-on technical leadership with people management, building production systems that directly impact our growth trajectory
• Lead & develop a team of 4+ ML and Backend engineers - hiring, mentoring, and setting technical direction
• Own pLTV strategy - architect and evolve our core predictive lifetime value models that inform millions in UA decisions
• Build production ML systems - from MMM algorithms to real-time forecasting models handling millions of daily predictions
• Drive cross-functional impact - partner with Growth, Product, and Finance to translate business problems into ML solutions
• Shape technical architecture - guide MLOps infrastructure, monitoring, and rapid iteration cycles
• Stay hands-on - contribute to modeling, architecture decisions, and technical problem-solving as needed