Machine Learning Staff Software Engineer, Search Personalization

Google•Mountain View, CA

18h•$207,000 - $300,000

About The Position

Google software engineers develop technologies used by billions of people to connect, explore, and interact with information. They work on projects critical to Google’s needs, with opportunities to move across teams and projects as the business evolves. Engineers are expected to bring versatility, leadership, and enthusiasm for solving problems across the full stack. This role manages project priorities, deadlines, and deliverables, and designs, develops, tests, deploys, maintains, and enhances software solutions. As part of the Discover Personalization team, this engineer helps deliver personalized content within Google Search by building foundational user models from interactions across Google products and applying them to Discover retrieval and ranking. The role addresses challenging machine-learning and quality problems, including neural deep retrieval, activity clustering, reinforcement learning, and multi-objective ranking. The broader Search team is reimagining information search and works to address complex engineering challenges while maintaining a universally accessible and useful experience. Individual pay depends on job-related skills, experience, and relevant education or training. The listed U.S. compensation is $207,000–$300,000, plus a 20% bonus target, equity, and benefits.

Requirements

Bachelor’s degree or equivalent practical experience.
8 years of experience in software development.
5 years of experience building and deploying recommendation-system models (retrieval, prediction, ranking, or embedding) in production, and experience building architecture in different modeling domains.
5 years of experience with ML design and ML infrastructure, such as model deployment, model evaluation, data processing, debugging, and fine-tuning.
5 years of experience testing and launching software products.
3 years of experience with software design and architecture.

Nice To Haves

8 years of experience with data structures and algorithms.
6 years of ML or quality experience working on recommendation systems.
Experience in recommender systems, clustering algorithms, SQL, and deep models.
Experience in C++, Dremel/F1, and TensorFlow.
Experience working with research.
Ability to drive quality projects end-to-end from design through implementation and launch.

Responsibilities

Design and implement personalized user models to optimize user happiness, including neural deep retrieval, deep neural network ranking/scoring, user/content clustering, and LLM-based retrieval-augmented generation models.
Build user and content clustering models for core personalization and ranking use cases.
Improve model performance and personalization precision/recall using advanced modeling techniques such as transformers, distillation, reward shaping, multi-task learning, and neural bandits, as well as feature engineering, automatic parameter tuning, and label quality engineering.
Scale model applications across modalities such as content, queries, videos, and notifications, and across use cases such as retrieval, ranking, content generation, and diversification.
Create next-generation real-time ML models that capture new user interests and world trends in seconds, and scale model training and serving to billions of users.
Manage project priorities, deadlines, and deliverables; design, develop, test, deploy, maintain, and enhance software solutions.