
Data Scientist
- Madrid
- Permanente
- Tiempo completo
- Own the technical implementation and maintenance of our recommendation engine in production.
- Productise machine learning models and pipelines (baseline + experimental logics).
- Ensure system performance, reliability, and low latency (e.g., Redis-based caching, catalog rotations, modifiers).
- Anticipate scaling challenges and design infrastructure to support larger catalogs, more complex segmentations, and higher traffic.
- Collaborate with scientists, analysts, and engineers to turn prototypes (new logics/experiments) into production-grade features.
- Develop and maintain data pipelines, ensuring clean transformations and robust experimentation frameworks.
- Partner with product and engineering to balance performance metrics with diversity, user experience, and content constraints.
- Strong proficiency in Python for ML, experimentation, and infrastructure.
- Solid knowledge of SQL and dbt for transformations.
- Experience with Databricks (or similar ML/data platforms).
- Proficiency with Redis (real-time serving, caching strategies).
- Hands-on experience deploying and monitoring ML models in AWS (SageMaker, Lambda, ECS, Step Functions).
- Familiarity with orchestration tools (Airflow, Prefect, Dagster) for pipeline reliability.
- Comfortable with Git/GitHub and CI/CD practices for ML systems.
- Strategic mindset: ability to anticipate infrastructure needs as models and experiments scale.
- Exposure to experimentation platforms (Amplitude, GrowthBook) and A/B testing frameworks.
- Knowledge of modern data stack tools (Snowflake, BigQuery, Fivetran).
- Interest in balancing data-driven optimization with pedagogical or brand-driven constraints (e.g., curated onboarding, character injection).