Staff Software Engineer, Quality, Google Cloud, Applied AI

About the job

Google Cloud’s mission is to make every business successful through AI by combining cutting-edge technology, infrastructure, and talent. AI/ML software engineers in Cloud bridge the gap between pioneering models and a massive product vehicle reaching billions. Our talent density and AI-powered tools drive rapid development, rooted in a culture of empowerment and a bias to action. In this role, you aren’t just building technology; you’re shaping the frontier of enterprise and driving the evolution of advanced models.

The GECX team is building agents that move beyond transactional support to build lasting, direct relationships with consumers. Our goal is to provide the best customer interfaces with multi-modal intelligence embedded - creating "full-stack concierges" capable of complex reasoning and seamless sales.

We are focusing on the "meta-layer" of AI: creating a suite of agents designed to build, test, and improve other agents. By leveraging Google’s foundational AI (Gemini and Vertex AI), we are transforming agent development from a manual, iterative process into a precise and highly optimized engineering artifact.

The Cloud Applied AI (AAI) powers business growth with Gemini Enterprise. Our portfolio includes Gemini Enterprise for Customer Experience (Shopping Agent, CX Agent Studio, Agent Assist, Vertex AI Search - Commerce, Customer Experience Insights), along with other vertical and domain packaged solutions. We enable high adoption and speed to value by building solutions that are quickly deployed, delivering new 0-to-1 capabilities with startup agility. Team members operate at the forefront of AI, collaborating directly with model builders with unprecedented speed. Join us to work on cutting-edge projects and shape the future of AI in a fast-paced, collaborative, and impactful environment.

Responsibilities

• Build the core logic for multi-modal customer support agents that execute complex reasoning across sales and support.
• Develop automated systems and tools that allow agents to iteratively build, test, and refine other agents.
• Architect the pathways that embed Gemini and Vertex AI intelligence directly into client-facing Cloud infrastructure.
• Establish engineering benchmarks to replace manual "trial-and-error" testing with automated, high-fidelity optimization.
  
• Take ownership of AI quality for production systems by defining technical metrics aligned with business goals, implementing evaluation frameworks, designing experiments, analyzing loss patterns, and driving improvements through system changes or training data enhancements.