Minimum qualifications:- Bachelor's degree or equivalent practical experience.
- 8 years of experience designing, building, and operating large-scale distributed systems, with a focus on scalability, fault tolerance, and reliability.
- Experience developing recommender/ranking/prediction systems for personalized content delivery.
- Experience in building and architecting ML systems and infrastructure (e.g., for model training, evaluation, deployment, serving).
- Experience working with consumer-facing video, audio or streaming platforms.
Preferred qualifications:- Experience in building and deploying recommendation systems models (retrieval, prediction, ranking, personalization, search quality, embedding) in production.
- Experience in distributed Machine Learning and Machine Learning infrastructure, distributed systems and with Machine Learning algorithms at scale.
- Experience in designing, building, and operating large-scale distributed systems, with a focus on scalability, fault tolerance, and reliability.
- Experience in Machine Learning model development and deployment frameworks (e.g., PyTorch, Tensorflow, Jax, Ray), AI accelerators (e.g., TPUs, GPUs), model architectures (e.g., encoders, decoders, transformers), or APIs.
- Experience in search and information retrieval.
About the jobAs a (TL) Technical Lead, you will work on improving Machine Learning (ML) algorithms and end-to-end solutions to empower live recommendations and grow live ecosystems responsibly. You will set up growth metrics and goals, conduct analysis and research to identify growth areas, and lead a team of engineers to iterate experiments toward launch.
Additionally, you will communicate across YouTube engineering teams and leads, to align with the design direction and future plans of your projects. In this position, you will work with YouTube Discovery teams (e.g., Home, Shorts, WatchNext, Notifications, Living Room), Live Infrastructure, and Live Experience teams, and collaborate with Google DeepMind, YouTube Knowledge, and YouTube Trust and Safety (TnS) teams.
Individual pay is determined by factors including job-related skills, experience, and relevant education or training.
US: $207000 - $300000 (USD) 20% bonus target equity benefits
Learn more about benefits at Google .
Responsibilities - Lead the technical goal and architecture for YouTube Live discovery and recommendation ML systems.
- Develop state-of-the-art deep learning models to improve real-time engagement and viewer retention on live streams.
- Scale high-throughput, low-latency machine learning pipelines to handle massive real-time streaming data concurrent traffic.
- Mentor junior and senior engineers, fostering technical growth and engineering excellence across the ML organization.
- Design ranking, retrieval, and candidate generation algorithms tailored for live and real-time content.