Philo: a streaming service for TV and movie lovers
At Philo, we’re a group of technology and product people who set out to build the future of television, marrying the best in modern technology with the most compelling medium ever invented — in short, we’re building the TV experience that we’ve always wanted for ourselves. In practice this means leveraging cloud delivery, modern tech stacks, machine learning, and hand-crafted native app experiences on all of our platforms. We aim to deliver a rock solid experience on the streaming basics, while cooking up next generation multi-screen and multi-user playback.
Data at Philo
Data underpins everything we do at Philo: making informed business decisions; analyzing and improving the quality of our streaming experience; running product experiments to optimize our signup flows and improve user journeys; and making it effortless for our users to find the perfect thing to watch. Philo serves over a billion streams to its users every year, generating a wealth of data that we leverage at all levels of the organization. Philo’s data pipeline processes nearly 8 trillion events per year into our petabyte scale data lake, where we run over 30k ETL and BI queries every day to bring data-driven insights to our team.
On the Data team, we’re looking for people who are comfortable working on a variety of interesting engagement, content discoverability, experimentation, acquisition, and retention-related problems across our streaming service. You’ll be working closely with other data scientists, analysts, and engineers to build and deploy solutions directly for our service. In addition, you’ll work with stakeholders in other departments to understand our business needs and deliver business-focused data insights to help the entire team thrive.
We are passionate about problem-solving and providing data-informed insights for the entire company, using both cutting-edge techniques and proven practices in close collaboration with every department. To complete our work we build on modern open-source tools including dbt, GrowthBook, Robyn, Superset, and PyTorch as well as SaaS tools such as Segment, Redshift, SageMaker, AWS Glue, Mode, Avo, and BigEye.
Some of the recent projects our Data Science team members have worked on include:
- Building marketing mix models and multi-touch attribution models to optimize customer lifetime value and predict RoAS (Return on Ad Spend)
- Modeling to determine which early product behaviors predict conversion
- Running experiments to evaluate and improve our ML-based content recommendation/personalization system
- Building data models for analysis of lifecycle marketing communications impact
- Modeling to analyze the impact of Quality of Experience events (e.g. rebuffering) on customer engagement and other business metrics.
- Data infrastructure engineering work including data warehouse cluster upgrades, per-query infra cost optimization, implementation of Apache Iceberg data storage, and evaluating alternative data warehouse technologies.
- Price sensitivity research and competitive market analyses
Source ⇲
