The new Posts Discovery team will be directly responsible for Posts growth and quality efforts. Posts are a new fast-growing content format on YouTube used by creators to share text, images, polls, quizzes and are already enjoyed by 300M+ daily engaged users. Our team is responsible for recommending posts safely across the entire YouTube ecosystem, including YouTube’s Home page, Shorts Feed, WatchNext, Search, Notifications, and dedicated vertical experiences such as News. In short, we aim to serve appropriate posts to the appropriate users at an appropriate time.
In the next couple years, the team’s mission is to grow Posts as a primary content on YouTube via widely expanded recommendation and a dedicated Posts Feed with monetization, incentivize and inspire high quality Posts creation, and ultimately drive more YouTube visits via Posts recommendation.
In this role, you will tech-lead a team of AI/ML software engineers to grow the YouTube Posts ecosystem by recommending Posts that are aligned with users’ dynamically changing interests. The YouTube Posts discovery models are a suite of large-scale AI/ML systems designed to model users’ interests by leveraging Google-wide data sources, understanding Posts’ content and recommending the right content to the viewers. Designed for multi-task learning across various surfaces, these models are applied to numerous downstream tasks, including retrieval, user action predictions, rich user model generation, and knowledge distillation for training more compact models.At YouTube, we believe that everyone deserves to have a voice, and that the world is a better place when we listen, share, and build community through our stories. We work together to give everyone the power to share their story, explore what they love, and connect with one another in the process. Working at the intersection of cutting-edge technology and boundless creativity, we move at the speed of culture with a shared goal to show people the world. We explore new ideas, solve real problems, and have fun — and we do it all together.Individual pay is determined by factors including job-related skills, experience, and relevant education or training.
US: $207000 - $301000 (USD) + 20% bonus target + equity + benefits
Learn more about benefits at Google.
Responsibilities
- Define technical strategy and solutions for enhancing YouTube Posts discovery models and systems to accelerate viewer and creator growth while improving user satisfaction.
- Provide technical leadership on high-impact projects. Manage project priorities, deadlines, and deliverables. Design, develop, test, and deploy large-scale recommendation models, novel model architectures, and optimize ML infrastructure to drive the growth of the Posts ecosystem.
- Partner with engineering, product, data-science to convert business goals into scalable technical solutions that grow the Posts ecosystem.
- Facilitate alignment and clarity across teams on goals, outcomes, and timelines. Influence and coach engineers on the team.
- Lead and mentor a team of engineers.
Qualifications
Minimum qualifications:
- Bachelor’s degree or equivalent practical experience.
- 8 years of experience in software development.
- 5 years of experience in software development.
- 3 years of experience in a technical leadership role leading project teams and setting technical direction.
- Experience building and deploying recommendation systems models (retrieval, prediction, ranking, embedding) in production and building architecture in different modeling domains.
Preferred qualifications:
- Master’s degree or PhD in Engineering, Computer Science, or a related technical field.
- 8 years of experience with data structures and algorithms.
- Experience with one or more of the following: large-scale recommendation or search systems, reinforcement learning (e.g., sequential decision making), ML infrastructure, or specialization in another ML field.
- Experience in people management, or interest in developing into a people manager.
- Experience of applying machine learning to improve user recommendations through fast experimentation and metric-driven iterations.