Join Google Cloud as a GenAI Forward Deployed Engineer (FDE) and pioneer the integration of cutting-edge AI into customer production environments. You will act as an embedded "innovator-builder," crafting and deploying bespoke agentic solutions. Your role involves overcoming production blockers, solving complex integration challenges, and ensuring data readiness for AI.

This position offers a unique opportunity to provide expert deployment of advanced AI systems. You will also serve as a crucial feedback conduit, translating real-world field insights into actionable product road map improvements for Google Cloud. Embed directly with engineering teams at our largest clients, transforming Google's developer AI tools like Gemini Code Assist and associated SDKs/CLIs into robust, production-grade workflows.

You will identify and resolve SDLC bottlenecks, taking ownership from discovery and build through to rollout, hardening, and ensuring long-term reliability. This is an exciting chance to lead the AI revolution within Google Cloud's Go-To-Market team, leveraging Google's unparalleled AI portfolio, including frontier Gemini models and the Vertex AI platform.

Collaborate closely with DeepMind's engineering and research experts to tackle intricate customer challenges. Be a catalyst for our mission, drive customer success, and help define the future of cloud computing.

Develop sophisticated AI applications, transforming rapid prototypes into production-ready agentic workflows that deliver tangible ROI.

Architect and implement the crucial connections between Google's AI products and customer live infrastructure, including APIs, legacy data systems, and security protocols.

Design and deploy robust agentic developer workflows on Google Cloud's AI stack. This includes managing large-scale refactors, language migrations, and establishing automated code review and incident resolution processes.

Collaborate with customer staff engineers and leadership to pinpoint core SDLC inefficiencies, such as legacy system migration challenges, inadequate test coverage, or slow review cycles. Define clear success metrics for these initiatives.

Integrate Google's agentic systems with existing customer tools and ISVs (e.g., Teamwork Graph, GitLab, ServiceNow, Slack) using advanced protocols like MCP and A2A.

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

Possess a minimum of 8 years of experience in cloud computing or a client-facing technical role.

Demonstrate hands-on experience deploying, scaling, and debugging Large Language Model (LLM) or agent-based systems in live production environments. This includes expertise with relevant tools, memory management, orchestration, evaluation, tracing, and cost/latency optimization.

Proven track record of end-to-end technical ownership for engineering projects, including successful management of executive stakeholders.

While not mandatory, a Master's degree or PhD in AI, Computer Science, or a related technical field is preferred. Experience with multi-agent systems using frameworks like LangGraph or CrewAI, and advanced patterns such as ReAct or hierarchical delegation, is highly advantageous.

Familiarity with agentic frameworks, harness layers (e.g., Google's ADK), and protocol interoperability (MCP, A2A) across third-party platforms (like ServiceNow), as well as understanding the DevSecOps security ecosystem, is beneficial.

Knowledge of LLM-specific metrics (e.g., tokens/sec, cost-per-request) and techniques for optimizing state management and detailed tracing is also preferred.