Join YouTube and be at the forefront of innovation, empowering global storytelling through cutting-edge technology. We are seeking a Forward Deployed Engineer specializing in Generative AI to bridge the gap between rapid prototyping and production-ready AI applications. This role offers a unique opportunity to shape the future of AI at YouTube, driving measurable impact and enhancing user experiences.

At YouTube, we foster a collaborative environment where creativity and technology converge. We are passionate about giving everyone a voice and connecting people through shared stories. If you're driven by innovation and want to contribute to a platform that impacts billions, this is your chance.

Serve as the primary engineering contact for deploying sophisticated AI applications, transforming initial concepts into robust, AI-powered solutions like multi-agent systems and MCP servers. You will manage the complete software development lifecycle, from conceptualization and planning to coding, testing, and deployment. This includes authoring detailed technical designs, writing maintainable code, developing intuitive front-end interfaces, and ensuring successful delivery from scoping to final launch.

Key responsibilities involve prototyping proof-of-concepts using advanced Generative AI technologies like LLMs and RAG to demonstrate feasibility to stakeholders. You'll translate complex business challenges into practical software solutions and build high-performance evaluation frameworks to guarantee the accuracy, safety, compliance, and low latency of agentic systems. Additionally, you will proactively identify and resolve technical obstacles hindering AI maturity, such as data readiness issues, integration complexities, edge-case management, and state management.

A Bachelor's degree in Computer Science, Electrical Engineering, Mathematics, or a related quantitative field, or equivalent practical software development experience, is required. You should have a minimum of 4 years of experience in full-stack software development and system design. Proficiency in back-end languages such as Java, Python, or C++, and front-end languages like JavaScript or TypeScript, is essential.

Experience with database technologies, including SQL and NoSQL, is mandatory. A strong background in Generative AI, encompassing Large Language Models (LLMs), development workflows, and practical use cases, is also a key requirement. Preferred qualifications include extensive experience with cloud or microservice architectures, building multi-step LLM applications, designing databases (including vector databases), and resolving data-readiness challenges for AI systems. Experience in Site Reliability Engineering, DevOps practices, and developing LLM evaluation pipelines is highly valued, alongside proven ability to collaborate with stakeholders on project requirements and go-to-market strategies.