At Netflix, we strive to entertain and to bring joy to people across the world through amazing stories. With a catalog spanning thousands of titles and a diverse member base spanning over 125+ million accounts, recommending the right titles/assets at the right time for each member is crucial. One of the teams powering this effort is the Data Systems for Personalization team, which builds scalable Machine Learning infrastructure for accelerating innovation for Netflix recommendations, content promotions, and search algorithms.
In this role, you will have the opportunity to build the next generation ML infrastructure to help us scale our recommendation algorithms as we find and entertain our next 100 million members. You will be working closely with ML researchers, product managers and engineers in the Personalization and Recommendations domain to help them scale their adhoc explorations and to execute member facing A/B tests. This role will allow you to gain intimate knowledge of Netflix Personalization, while working for a unique and pioneering company that is redefining how video content is consumed globally.
Here are some examples of the types of things you would work on:
- Build large scale Training data infrastructure and framework for feature generation that ensures we use consistent data and features for both offline model training and online scoring.
- Build generalized contextual bandits framework for Explore/Exploit pipelines.
- Build real-time and stream-processed infrastructure for near-line personalized Billboard recommendations, Artwork personalization etc.
- Build generic high-scale frameworks that is used by application teams to do online scoring and to pre-compute recommendations.
- With more than 1000 hours of Original content, build the infrastructure to compute real-time insights on the performance of Original shows for better personalization and targeting.
To learn more, here are some talks/blog posts from the team:
- You can learn more about Netflix’s culture of Freedom and Responsibility, that presents an opportunity to work with some of the best and the brightest, allowing you to make a difference to our business in a meaningful way.
- 4+ years of relevant software engineering experience
- Experience working on Machine Learning Infrastructure at a web-scale organization
- Experience with large-scale distributed data processing systems like Apache Spark
- Experience working with functional languages like Scala
- Excellent communication and people engagement skills
Even better if you have experience with any or all of
- Experience in Personalization/Recommendation domain
- Experience building stream processing applications on Apache Spark, Flink or Samza
- Experience with Cloud Computing platforms like Amazon AWS