About the job
In this role, you will work with deep models which serve large-scale traffic to Billions of YouTube users making real-time recommendations. The team is responsible for the entire end-to-end life-cycle from researching, prototyping, building, deploying and maintaining all these models. We develop new models ground up for new products and ad experiences on YouTube. We also work on designing new model architectures, feature engineering, metrics and evaluation strategies for increasing model performance.
Responsibilities
Work on identifying innovative solutions for various product, user, advertiser optimization problems.
Build end-to-end machine learning systems on large-scale data (billions of YouTube queries).
Research novel deep model architectures, read papers, implement and deploy them.
Build models from inception to launch: Collect ground truth, exploratory models, feature engineering, deep model architectures, live experiments on YouTube users, tuning, metrics analysis.
Data analysis both offline on model prediction accuracy, and online on live experiments on business critical metrics.
Qualifications
Minimum
Bachelor’s degree or equivalent practical experience.
5 years of experience with software development in C++ and Python.
3 years of experience testing, maintaining, or launching software products, and 1 year of experience with software design and architecture.
3 years of experience with one or more of the following: Speech/audio (e.g., technology duplicating and responding to the human voice), reinforcement learning (e.g., sequential decision making), ML infrastructure, or specialization in another ML field.
3 years of experience with ML infrastructure (e.g., model deployment, model evaluation, optimization, data processing, debugging).
Preferred
Master's degree or PhD in Computer Science or related technical field.
1 year of experience in a technical leadership role.
Experience in data analysis for building and optimizing machine learning models, such as Neural Networks and Recommender Systems, specifically for large-scale Ads platforms.
Passion to work in a fluid, high-visibility team.
Passion to work in a cross-functional, collaborative environment that involves establishing mutually-beneficial relationships with research and product teams.