As a GenAI Forward Deployed Engineer at Google Cloud, you'll be an embedded builder, connecting cutting-edge AI products with real-world customer applications. You won't just advise; you'll actively code, debug, and deliver bespoke agentic solutions directly within client environments. Your role involves overcoming production hurdles, tackling integration complexities, ensuring data readiness, and resolving state-management issues to bring AI to enterprise maturity.

You’ll play a dual role: providing expert deployment of intricate AI systems and serving as a vital feedback channel. Your field insights will directly influence Google Cloud’s future product roadmap. You will embed with engineering teams at major clients, transforming Google's developer AI tools like Gemini Code Assist, IDEs, SDKs, and CLIs into production-ready workflows. This involves identifying operational slowdowns, designing systemic solutions, and managing them end-to-end, from discovery and build to rollout, hardening, and ensuring long-term reliability.

Serve as a developer for complex AI applications, transitioning from rapid prototypes to production-grade agentic workflows (e.g., multi-agent systems, Model Context Protocol (MCP) servers) that drive measurable Return on Investment (ROI).

Architect and code the connective tissue between Google’s AI products and customer's live infrastructure, including APIs, legacy data silos, and security perimeters as part of an expert team.

Design and deploy production-grade agentic developer workflows on Google Cloud's AI stack, executing large-scale refactors, language migrations, Specification-to-Pull Request pipelines, and automated review/incident-to-fix loops.

Embed with customer's staff engineers and leaders to identify core SDLC bottlenecks, such as legacy migrations, test coverage, review latency, or onboarding friction, and define success metrics.

Integrate Google’s agentic systems into the customer's existing ISV and tools (e.g., Teamwork Graph, GitLab, ServiceNow, Slack) leveraging MCP and A2A protocols.

A Bachelor’s degree in Engineering, Computer Science, or a related field, or equivalent practical experience is required.

We seek candidates with at least 8 years of experience in cloud computing or a technical customer-facing role.

Demonstrated experience in deploying, scaling, and debugging Large Language Model (LLM) or agent-based systems in production environments, including expertise in relevant tools, memory management, orchestration, evaluation, tracing, and cost/latency profiling, is essential.

Experience with end-to-end technical ownership of engineering projects, including managing relationships with executive stakeholders, is also a key requirement.

Preferred qualifications include a Master’s degree or PhD in AI, Computer Science, or a related technical field. Experience implementing multi-agent systems using frameworks like LangGraph or CrewAI, and working with agentic frameworks such as Google's Agent Development Kit (ADK), is highly desirable. Familiarity with protocol-level interoperability (MCP, A2A) across third-party ISV platforms like ServiceNow, and knowledge of LLM-native metrics for optimizing state management and tracing, are considered advantageous.