Design and implement retrieval and ranking architectures for personalized recommendations
Work with large-scale user behavior and content data to extract meaningful signals
Build end-to-end ML systems: data processing, feature engineering, training, evaluation, deployment, monitoring
Run A/B tests and offline evaluations to measure model impact and guide improvements
Collaborate with product and engineering teams to align recommendations with business goals
Continuously monitor model performance
Strong hands-on experience building recommendation systems or ranking models
Deep understanding of machine learning fundamentals and evaluation methodologies
Experience working with large-scale data (SQL, Spark, or distributed data systems)
Proficiency in Python and modern ML frameworks (PyTorch, TensorFlow)
Understanding of core ML concepts: supervised/unsupervised learning, evaluation metrics, feature engineering
Experience deploying ML models to production and maintaining them over time
Ability to balance experimentation with production reliability
Experience with real-time recommendation systems
Knowledge of search / information retrieval systems
Familiarity with feature stores, model monitoring, and ML infrastructure
Experience in media, music, or consumer-facing personalization products
Work on high-impact ML systems used by real users at scale
Ownership over meaningful technical decisions, from modeling to production
Collaborative, product-driven environment with strong engineering culture
A supportive and dynamic startup culture where your ideas and contributions truly matter
Opportunities for growth, learning, and shaping the future of our recommendation stack
Skills Required
- Hands-on experience building recommendation systems or ranking models
- Deep understanding of machine learning fundamentals and evaluation methodologies
- Experience working with large-scale data (SQL, Spark, or distributed data systems)
- Proficiency in Python and modern ML frameworks (PyTorch, TensorFlow)
- Understanding of supervised/unsupervised learning, evaluation metrics, and feature engineering
- Experience deploying ML models to production and maintaining them over time
- Ability to balance experimentation with production reliability
- Experience with real-time recommendation systems
- Knowledge of search / information retrieval systems
- Familiarity with feature stores, model monitoring, and ML infrastructure
- Experience in media, music, or consumer-facing personalization products
What We Do
GRAI is an AI music research lab based in Warsaw, Poland, dedicated to building foundation models and interaction primitives for the future of music. The company develops AI-powered tools that enable users to interactively remix, transform, and share songs, aiming to make music more social and interactive while ensuring artists maintain control and potentially benefit from new royalty streams.
