Software Engineer, Agentic AI and LLMs, Ads

About The Job

Google's software engineers develop the next-generation technologies that change how billions of users connect, explore, and interact with information and one another. Google Ads powers digital commerce for millions of global businesses. Within Google Ads, the team is creating the next wave of intelligent, autonomous systems by building conversational and agentic workflows that resolve complex advertiser inquiries across chat, email, and virtual meetings. This role bridges frontier foundation models with massive-scale distributed infrastructure to build reliable, helpful, and safe enterprise assistants, working on state-of-the-art AI and taking on problems at an unparalleled scale to build the next generation of advertising technology.

Key Responsibilities

• Write product or system development code using Java, Python, Go, or C++ to build and optimize high-throughput backend services, storage schemas, APIs, and data pipelines for massive-scale GenAI systems.
• Collaborate with peers and stakeholders through technical design and code reviews to ensure best practices amongst available technologies, focusing on style guidelines, checking code in, accuracy, testability, and efficiency.
• Contribute to existing technical documentation or educational developer content and adapt engineering specs based on system/program updates, prompt engineering variations, and internal and external user feedback loops.
• Triage issues and debug/track/resolve production anomalies by analyzing the sources of issues and their impact on hardware, network, or service operations, system latency, and output quality.
• Implement solutions in specialized ML areas utilizing ML infrastructure to contribute to model optimization, data processing, and Tier 2 on-call reliability.

Requirements & Tech Stack

• Software development in one or more programming languages (e.g., Java, Python, Go, or C++).
• Experience with one or more of the following: Speech/audio systems, reinforcement learning (sequential decision making), ML infrastructure, or a distinct specialization in another machine learning field.
• End-to-end Machine Learning (including model deployment, model evaluation, data processing, and debugging).
• Data structures or algorithms in either an academic or industry setting.
• LLMs, prompt design/optimization (e.g., APO), or modern agentic orchestration frameworks.
• Full-stack development across back-end services, database schemas, APIs, and front-end frameworks (e.g., Dart, JavaScript, or TypeScript).
• Experience developing accessible technologies that comply with global usability and accessibility standards.

Qualifications

• Bachelor’s degree in Computer Science, Mathematics, a related technical field, or equivalent practical experience.
• 2 years of experience with software development in one or more programming languages (e.g., Java, Python, Go, or C++), or 1 year of experience with an advanced degree.
• 1 year of experience with one or more of the following: Speech/audio systems, reinforcement learning (sequential decision making), ML infrastructure, or a distinct specialization in another machine learning field.
• 1 year of experience with end-to-end Machine Learning (including model deployment, model evaluation, data processing, and debugging).
• Preferred: Master's degree or PhD in Computer Science, Computer Engineering, Machine Learning, or related technical fields.
• Preferred: 2 years of experience with data structures or algorithms in either an academic or industry setting.
• Preferred: 1 year of experience with LLMs, prompt design/optimization (e.g. APO), or modern agentic orchestration frameworks.
• Preferred: Experience developing accessible technologies that comply with global usability and accessibility standards.
• Preferred: Experience with full-stack development across back-end services, database schemas, APIs, and front-end frameworks (e.g., Dart, JavaScript, or TypeScript).