28 days ago
Rome, ItalySenior
Responsibilities
- Design, build, deploy, and monitor production machine learning models and pipelines for audience segmentation and affinity systems.
- Build and maintain high-volume feature engineering and data pipelines using Spark, Databricks, Python, and SQL across tables with tens of billions of rows.
- Implement MLOps practices including model registries, offline and online evaluation, experiment tracking, and data/model drift and quality monitoring.
- Integrate ML systems with the Audience API, User Profile API, Kafka topics, and downstream activation platforms including DV360, Braze, and TTD.
- Design offline evaluations and A/B tests, tune model hyperparameters, and develop new data signals such as Store Trip Data.
- Operate production backend and data systems, including participation in the on-call rotation.
- Ensure modeling and data pipeline initiatives comply with GDPR, CCPA, and consent-management requirements.
- Collaborate with Product Analytics, Marketing Science, Data Engineers, and Software Engineers to support revenue objectives.
- Use AI-assisted development tools such as Cursor and Claude Code to improve engineering throughput.
Requirements
- Proven experience owning the full production ML lifecycle, including feature engineering, model training, evaluation, deployment, and monitoring.
- Strong software engineering fundamentals and experience operating production backend and data systems end to end.
- Strong proficiency in Python, Spark, SQL, and Databricks, with experience building distributed data pipelines at scale.
- Hands-on ability to build, tune, and evaluate models with grounding in statistics, hyperparameter tuning, and experiment design.
- Experience with ML lifecycle tools such as MLflow, model registries, and production monitoring for drift and quality.
- Hands-on use of AI development tools such as Cursor or Claude Code.
- Bachelor's degree in Computer Science, Mathematics, Physics, Engineering, or a related quantitative field.
- Fluent English communication skills and availability overlapping North American hours from 9am to 12pm EST.
- Ad-tech or programmatic advertising experience is preferred.
- Privacy engineering experience and familiarity with GDPR and CCPA are preferred.
- Deep Databricks platform administration knowledge is preferred.
- Familiarity with LLM platforms such as OpenAI and Gemini and embedding research is preferred.
Benefits
- Flexible hybrid work model with full remote availability from Europe and offices in Milan, Barcelona, and Sofia.
- Learning opportunities and regular feedback sessions.
- Modern central offices with fresh snacks, coffee, and ergonomic setups.
- Team events including offsites, happy hours, company parties, and celebrations.
- Company-provided equipment and workspace setup support.
- Additional country-specific benefits based on local contracts and practices.
Tech Stack
Categories
About ShopFully
ShopFully builds a “drive-to-store” digital advertising platform that connects online shoppers with local retailers’ offers through its apps, websites, and a large publisher network. Retailers and brands use its AI-based targeting and ad products to promote weekly deals and measure in-store impact, paying for media and campaign services. Founded in 2012 and headquartered in Milan, it operates across 25 countries and reports connecting around 200 million shoppers for hundreds of retail clients.