Machine Learning Engineer, Search and Shopping

Build low-latency machine learning for Search and Shopping Ads at Google from Mountain View, CA (onsite). This role focuses on creating and scaling predicted click-through rate (pCTR) models that are designed to run within tight serving and return-on-investment budgets, while integrating ads into emerging AI-driven search experiences. You will work closely with DeepMind, Research, and Ads Machine Learning teams to translate modeling advances into production systems.

What you’ll do

• Own technical architecture and cross-team strategy for Search and Shopping Ads pCTR modeling, partnering closely with DeepMind, Research, and Ads Machine Learning.
• Design, prototype, and scale high-capacity pCTR architectures that maximize modern Tensor Processing Unit (TPU) performance while meeting strict low-latency serving and ROI constraints.
• Develop modeling approaches that capture deep user history and nuanced attention signals, integrating ads into emerging AI Search experiences such as AI Overviews and AI Mode.
• Engineer loss functions and calibration methods that connect complex business objectives to measurable top-line and auction improvements.
• Build agentic machine learning workflows to automate and accelerate model architecture and feature space discovery.

What you bring

• Bachelor’s degree or equivalent practical experience.
• 8 years of experience with software development, including 5 years in large-scale machine learning, deep learning, neural networks, or recommendation systems.
• Experience designing and implementing large-scale production deep learning or neural network architectures under latency and computational constraints.
• Experience leading cross-functional technical projects and mentoring other engineers.

Helpful experience

• PhD degree in Computer Science, Machine Learning, Artificial Intelligence, or a related field.
• Experience with agent-driven ML exploration, hyperparameter tuning, or automated model architecture search.
• Experience with one or more areas such as loss engineering for business objectives, joint modeling across distinct prediction stacks, or hardware-aware ML optimizations (for example, leveraging dense compute and TPUs effectively).
• Familiarity with ads prediction systems, auction dynamics, or serving infrastructure (such as AdBrain, Admixer).
• Ability to collaborate with peer technical leads and advanced ML research organizations (for example, DeepMind or Google Research) to bring academic and exploratory techniques into production.

Tech you’ll work with

• Tensor Processing Unit (TPU), large-scale machine learning, deep learning, neural networks, and recommendation systems
• Sequence modeling and agentic artificial intelligence workflows
• Agentic machine learning workflows, loss functions, and calibration methods

Compensation and benefits

US base salary: $207,000 - $300,000 per year + 20% bonus target + equity + benefits. Learn more about benefits at Google.