Data Scientist – Applied ML, Recommendations

This is a fully remote position, open to applicants in Spain.

📋 Description

• Take charge of the production recommendation infrastructure: maintain and enhance the systems that deliver personalized content to millions of users, ensuring reliability, low latency, and scalability as the catalog and user base expand.

• Investigate and prototype advanced recommendation algorithms: explore innovative methods - deep learning models, contextual bandits, session-based recommendations, graph-based approaches - assess their potential, and conduct controlled experiments to validate improvements before production.

• Create ML models and pipelines: transform prototypes (developed by yourself or the team's Data Scientist) into production-ready, monitored, and maintainable features integrated into the live recommendation engine.

• Design scalable infrastructure: foresee bottlenecks and construct systems capable of managing larger catalogs, more intricate segmentations, and increased traffic - including optimization of the serving layer, caching strategies, and orchestration of pipelines.

• Develop and sustain data pipelines in DBT and Databricks, ensuring clean transformations, data quality, and reliable experimentation frameworks for the team.

• Oversee model health in production: establish retraining strategies, identify drift, and ensure the quality of recommendations is continuously measured and maintained.

• Work closely with the Data Scientist and Senior Analyst to convert statistical insights and business requirements into engineering decisions.

⛳️ Requirements

• Proficient in Python for ML and infrastructure: strong Python abilities applied to model training, evaluation, deployment, and pipeline scripting. Produces production-quality, testable, version-controlled code - beyond just notebooks.

• SQL and DBT: solid SQL skills and practical experience with DBT for building and maintaining reliable transformation pipelines with clear data lineage and quality controls.

• ML production on AWS: practical experience in deploying and monitoring ML models using AWS services (SageMaker, Lambda, ECS, Step Functions). Understands model drift, monitoring strategies, and triggers for retraining.

• Batch ML model training and evaluation pipelines: design, construct, and maintain scalable machine learning training and evaluation pipelines that support recommendation systems and related personalization use cases. This includes developing robust, well-monitored workflows for model development, deployment, and continuous enhancement, while contributing to the evolution of the recommendation infrastructure toward more adaptive and responsive systems over time.

• Familiarity with advanced ML algorithms: knowledge of recommendation techniques beyond collaborative filtering - such as neural approaches (two-tower models, transformers for sequences), contextual bandits, and learning-to-rank. Able to evaluate and compare them rigorously.

• Experience with orchestration and CI/CD: familiarity with orchestration tools (Airflow, Prefect, or Dagster) for reliable, observable pipelines, and comfort with Git and CI/CD workflows for ML systems.

• Scalability and system design mindset: capable of anticipating infrastructure bottlenecks, reasoning through architectural trade-offs (batch vs. streaming, horizontal vs. vertical scaling), and linking engineering decisions to business outcomes.

• Nice to have: Experience with real-time or low-latency serving layers (Redis, DynamoDB, or equivalent) - the system is currently batch, but session-level adaptation is a future direction.

• Knowledge of experimentation frameworks for ML systems, including online evaluation of recommendation algorithms (A/B tests, interleaving, counterfactual evaluation).

• Familiarity with modern data stack tools (Snowflake, BigQuery, Fivetran).

• Exposure to knowledge graph or content graph methodologies for content-aware recommendation.

• Interest in balancing data-driven optimization with pedagogical or brand-driven constraints (e.g. content diversity goals, curated onboarding, character injection).

• Proficient in English: We’re a multicultural team providing a service in English, so while certifications aren’t necessary, fluency is essential. As a fully remote company, clear and effective spoken and written communication, especially in asynchronous and long-form formats, is vital for successful collaboration.

🏝️ Benefits

• Career Growth: Your growth drives our success! We invest in your development up to €2,000 per year for books and training; so you can continue learning and growing with us.

• Remote-Friendly: Work from wherever you’re most productive, whether it’s from home or our offices in Madrid, within a 2-hour difference from Spain (GMT+1). The choice is yours!

• Stock Options: Your contribution matters! You'll receive stock options, providing you the opportunity to own part of the company and share in its success.

• Home Office Setup: Create your ideal workspace with a €400 allowance for setup and €35/month for remote work expenses, because comfort fuels creativity!

• Meal Allowances: Receive €60/month on your Cobee card to enjoy meals at restaurants or food delivery; good food makes everything better!

• Flexible Compensation: Easily manage your meal, transport, and childcare expenses with Cobee, seamlessly integrating them into your payroll.

• Health Insurance: Access private health coverage at exclusive rates through Adeslas, conveniently deducted from your payroll, ensuring quality care made straightforward.

• Language Lessons: Learning never stops! Enjoy free language classes in Spanish and English to enhance your skills and stay connected in a global team.

• Visa Sponsorship: If you require a visa to work in the EU, we’ll manage the process and cover the costs to ensure a smooth transition.

• Company events: Yes! We’re a fully remote team spread across various countries, but we cherish opportunities to gather from time to time in different locations in Spain for team events and recharging during our fantastic off-sites!