ShopFully is seeking a Senior Machine Learning Engineer to join the Audience Platform team within Ad Products. This role, based in Rome, Italy with a hybrid work arrangement, owns and operates production ML systems and the backend infrastructure powering 1P, 2P, and 3P audience data across ShopFully platforms. It is an engineering first position focused on building and operating production ML systems end to end, not merely handing off code for production. You will apply hands on statistics, model selection, building, tuning, and experiment design, alongside strong software engineering fundamentals to build scalable pipelines on tens of billions of rows of data. Responsibilities include: design, build, deploy, and monitor production ML models and pipelines such as the IAB Segmentation Model, Retailer & Category Affinity Segments, and Custom Segment Toolkits; feature and data engineering at scale using Spark, Databricks, Python, and SQL with core tables containing tens of billions of rows; implementing robust MLOps practices including model registries, offline/online evaluation, experiment tracking (MLflow or equivalent), and monitoring for data/model drift and quality; ensuring models integrate with downstream services via Audience API, User Profile API, Kafka Topics, and activation integrations like DV360, Braze, and TTD; running offline evaluations and A/B tests to validate impact, optimize hyperparameters, and unlock new data signals (e.g., Store Trip Data); planning and executing modeling and data pipeline initiatives in line with GDPR, CCPA, and consent management; coll

ShopFully is seeking a Senior Machine Learning Engineer to join the Audience Platform team within Ad Products. This role, based in Rome, Italy with a hybrid work arrangement, owns and operates production ML systems and the backend infrastructure powering 1P, 2P, and 3P audience data across ShopFully platforms. It is an engineering first position focused on building and operating production ML systems end to end, not merely handing off code for production. You will apply hands on statistics, model selection, building, tuning, and experiment design, alongside strong software engineering fundamentals to build scalable pipelines on tens of billions of rows of data. Responsibilities include: design, build, deploy, and monitor production ML models and pipelines such as the IAB Segmentation Model, Retailer & Category Affinity Segments, and Custom Segment Toolkits; feature and data engineering at scale using Spark, Databricks, Python, and SQL with core tables containing tens of billions of rows; implementing robust MLOps practices including model registries, offline/online evaluation, experiment tracking (MLflow or equivalent), and monitoring for data/model drift and quality; ensuring models integrate with downstream services via Audience API, User Profile API, Kafka Topics, and activation integrations like DV360, Braze, and TTD; running offline evaluations and A/B tests to validate impact, optimize hyperparameters, and unlock new data signals (e.g., Store Trip Data); planning and executing modeling and data pipeline initiatives in line with GDPR, CCPA, and consent management; coll