Senior Staff Software Engineer, AI Agent Platform, Vertex

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.

As a part of the Cloud AI Agent Platform team (previously known as Vertex), you will focus on building highly differentiated, highly scalable, and easy-to-use GenAI products and services that enable customers to transform their business with GenAI. You will be responsible for building the high-performance, hyper-scale backend infrastructure that powers the Vertex AI APIs, serving millions of requests and enabling the next-generation of AI-driven applications. In this role, you will have a unique opportunity to be at the absolute forefront of the Generative AI revolution. You will be building the foundational API layer and infrastructure that serves massive foundation models (like Gemini) to the world. In this role, you will address unprecedented scaling issues, optimize for ultra-low latency, and design scalable systems that define how developers interact with AI. You will operate in a highly dynamic, incredibly changing environment where your work will have an immediate and massive impact on Google Cloud's most product area.

Individual pay is determined by factors including job-related skills, experience, and relevant education or training. Poland: zł640000 - zł655000 (PLN) + 25% bonus target + equity + benefits Learn more about[benefits at Google .

Responsibilities

• Architect, develop, and maintain horizontally scalable APIs and backend infrastructure tailored specifically for Generative AI workloads.
• Optimize the routing, load balancing, quota management, and data plane mechanisms that connect user API requests to backend ML serving clusters across massive fleets of TPUs and GPUs.
• Prototype and launch new API products rapidly in a highly collaborative environment, to expose the latest advancements in Google's foundation models.
• Collaborate closely with ML researchers, ML serving teams, and product managers to translate complex AI capabilities into intuitive, highly reliable enterprise-grade APIs.
• Define and implement best practices for API security, high availability, fault tolerance, and comprehensive observability across distributed systems.