Senior Software Engineer, Machine Learning, Discover Interest Modeling

Google•Mountain View, CA

1d•$174,000 - $252,000

About The Position

Google software engineers develop technologies used by billions of people and work on projects critical to Google's needs. The role calls for versatile engineers who can show leadership, take on new problems across the full stack, and contribute to Google's evolving technology. This position is on Discover, Google's personalized interest feed, one of the world's largest feed recommendation products. The role focuses on modeling people's long-term interests, favorite creators, and in-the-moment intent. These models provide important personalization signals for recommendations and feed ranking across Google. The retrieval and pre-ranking stack selects relevant items for each person from a continually refreshed corpus of articles, videos, creator posts, and AI-generated content. The position is part of Google Search, where the team works on complex engineering and infrastructure challenges while maintaining a universally accessible and useful experience for people around the world. Individual pay is determined by job-related skills, experience, and relevant education or training. The stated U.S. compensation is $174,000–$252,000, plus a 15% target bonus, equity, and benefits.

Requirements

Bachelor's degree or equivalent practical experience.
5 years of experience with machine learning algorithms and tools (e.g., TensorFlow), recommender systems, deep learning, or personalization.
3 years of experience testing, maintaining, or launching software products, and 1 year of experience with software design and architecture.
3 years of experience building and deploying recommendation system models in production, including retrieval, prediction, ranking, personalization, search quality, or embeddings, and experience building architecture.
Experience with deep learning architectures and related algorithms, such as Transformers.

Nice To Haves

Master's degree or PhD in Computer Science or a related technical field.
5 years of experience with data structures and algorithms.
1 year of experience in a technical leadership role.
Experience developing accessible technologies.

Responsibilities

Add predictive modeling of the interests and creators a user will engage with next, training with multi-objective goals such as engagement and satisfaction.
Redesign the interest vocabulary for much higher precision and evaluate learned alternatives to the current interest vocabulary.
Build deep, sequence-based token models that learn from long user activity histories across Google products.
Build offline evaluation that predicts online results, including profile-quality autoraters and retrieval and ranking metrics, and run well-sliced live experiments.
Design a shared token description, feature set, and training objectives across token types.