Data Scientist - RecSys (iGaming)

TL;DR

Data Scientist - RecSys (iGaming): Building large-scale production-grade recommendation systems impacting millions of players worldwide with an accent on end-to-end pipelines from data ingestion to model inference. Focus on developing and optimizing ML models for next-item prediction, integrating multi-modal data, and scaling for real-time processing.

Remote (Portugal, Global)

Company

Leading content provider to the iGaming and Betting Industry, powering Pragmatic Play with innovative, regulated, mobile-focused products including slots, live casino, sports betting, virtual sports, and bingo.

What you will do

• Design, implement, and optimize end-to-end recommendation pipelines from data ingestion to model inference.
• Build scalable ETL pipelines and develop ML models for recommendation systems.
• Research and prototype state-of-the-art approaches to improve recommendation quality and business metrics.
• Integrate multi-modal data and ensure pipeline robustness with testing and monitoring.
• Design A/B tests, build dashboards, and collaborate with engineers for production-ready solutions.

Requirements

• Strong Python experience with data science/ML libraries (Pandas, Polars, NumPy, scikit-learn, PyTorch, TensorFlow, JAX, Hugging Face).
• End-to-end ML systems on cloud platforms (Azure, GCP, AWS) including ETL, deployment, monitoring.
• Deep learning-based recommender systems for next-item prediction and sequential patterns.
• Efficient data pipelines for OLTP/OLAP, SQL/NoSQL databases (PostgreSQL, MySQL, Redshift, Snowflake, BigQuery, MongoDB, Cassandra).
• Unit/integration testing (Pytest), CI/CD, Docker containerization.

Nice to have

• Large-scale recommender systems (candidate generation, ranking, retrieval).
• Publications in deep learning conferences/journals.
• Azure Data Factory/AWS Glue/Google Cloud Dataflow.
• A/B testing design and metrics.
• Multi-modal models, transformer/LLM for recommendations.
• Distributed training/processing (Spark, Kafka, etc.).

Culture & Benefits

• Competitive compensation based on experience and impact.
• Professional and personal development opportunities.
• Work on state-of-the-art ML infrastructure at scale.
• Contribute to open-source and ML community.
• Flexible working hours and remote-friendly setup.
• Values: Persistence, Respect, Ownership.