Data Scientist

What We Do/Project We’re looking for a Senior Data Scientist with a strong foundation in predictive modeling, clustering, and statistical analysis. This role combines hands-on machine learning with close collaboration across business and product teams to build production-ready models that forecast content performance and reveal content insights. The ideal candidate is fluent in modern MLOps tools, proactively explores new approaches, and iterates based on user feedback to ensure solutions are interpretable, trusted, and adopted across the organization. Experience in the media/entertainment industry is a strong advantage, or other creative industries. The ideal candidate has experience building DS solutions to support, not replace, human judgment, and therefore has experience optimizing for results beyond just accuracy improvements, such as enriching insights and discussions. Job Responsibilities / Typical Day in the Role l Build and iterate on predictive models to project content performance • Test different model types (e.g., gradient boosting, regression) and iterate based on accuracy and user interpretability needs • Complete model experiments to validate hypotheses • Proactively identify opportunities to improve performance and contribute to model development roadmap Explore and segment content types • Use clustering, principal component analysis, and other unsupervised methods to identify patterns in performance drivers and content types • Experiment with GenAI to enrich data (e.g., augmenting metadata tagging or generating synthetic attributes) Collaborate with business users to refine models and drive adoption • Infuse models and model approach with users’ domain expertise and decision-making workflows • Present early model outputs in accessible ways to solicit feedback and identify gaps, overlooked variables, and implicit assumptions from users • Interpret user feedback and adapt model design and underlying data to prioritize interpretability, usability, or explainability where required to build trust and drive adoption Maintain and monitor models • Work with ML Engineers to deploy models in production, including API endpoints, and establish ML pipeline • Contribute to shared libraries and modeling best practices across the data science team Partner with product and platform teams to deliver impact • Contribute to design and implementation of new products where data science models will be embedded, built by agile product PODs • Collaborate with data architects, data engineers, and broader platform team to facilitate technical discussions and enrich the data available for data science Must Have Skills / Requirements • Proven experience as a Data Scientist • 4+ years of experience • Python and common ML library experience • 4+ years of experience; (e.g., scikit-learn, XGBoost, pandas). • Familiarity with AWS tools, especially SageMaker, or equivalent cloud-based ML environments • 4+ years of experience Nice To Have Skills / Preferred Requirements • Experience in media & entertainment industry is a strong advantage but not required • SQL fluency is a plus Soft Skills • Curiosity and capability to work in an experimental stage of development to test hypotheses and adjust approaches to deliver the most value to business users • Experience building predictive models, especially with limited sample sizes • Understanding of clustering and dimensionality reduction techniques • Exposure to generative AI models (e.g., LLMs, diffusion models) and an interest in applying them to real-world data problems • Strong communication skills and the ability to translate data science work into business value as well as translate business user needs into data science Technology Requirements • Strong skills in Python and common ML libraries (e.g., scikit-learn, XGBoost, pandas). • Familiarity with AWS tools, especially SageMaker, or equivalent cloud-based ML environments • Experience building predictive models, especially with limited sample sizes • Understanding of clustering and dimensionality reduction techniques • Exposure to generative AI models (e.g., LLMs, diffusion models) and an interest in applying them to real-world data problems Additional Notes • Sourcing in CA – Burbank. • Hybrid – schedule flexible. #DICE