Penguin Random House is looking for a Machine Learning Scientist to join our Data Science team. You will help build and improve personalization products, including recommender systems for our websites, email programs, and online marketing initiatives. This role owns recommender models end-to-end, from development and deployment to monitoring, in close partnership with business stakeholders, platform engineers, and the personalization group.

What You'll Do

Build, evaluate, and iterate on recommender systems and personalization models that improve discovery across our digital channels.
Develop models supporting online marketing and engagement use cases, such as customer segmentation, propensity modeling, audience targeting, and engagement prediction.
Define success metrics and use offline evaluation plus online experimentation, including A/B tests, to validate performance, monitor quality, and drive iteration.
Partner with engineering and platform counterparts to productionize models, including repeatable training, deployment workflows, monitoring, and refresh strategies.
Diagnose model performance issues and data quality problems, communicating findings and recommended actions clearly to stakeholders.
Write maintainable, production-minded code and contribute to team standards for code review, documentation, reproducibility, and testing.
Stay current with advances in recommender systems and applied AI, bringing practical ideas back to the team.

What We're Looking For

A Master's degree with 2+ years of applied work experience OR a PhD in Computer Science, Machine Learning, Engineering, Operations Research, Statistics, or a related quantitative field.
Strong proficiency in Python and common ML frameworks and libraries like PyTorch or TensorFlow.
Strong SQL skills and experience working with large datasets for feature development, analysis, and validation.
Experience taking models from development to production, such as for batch scoring, APIs, or downstream integration.
Solid understanding of experimentation and measurement.
The ability to use the latest AI tools to develop well-designed and robust software.
Strong communication skills and the ability to translate between business goals and technical solutions.

Nice to Have

Experience with recommender systems, personalization, ranking/retrieval, or marketing targeting models.
Familiarity with cloud and modern data/ML tooling like AWS, Databricks, Docker, Kubernetes, Spark, or similar.
Exposure to MLOps concepts and tooling for model registries, pipelines, monitoring, and reproducibility.
Experience with real-time or near real-time prediction systems.