Forward Deployed Engineer, Google Cloud, AI Expert

About the role

We are seeking a Forward Deployed Engineer (FDE) with deep expertise in Google Cloud and applied AI to embed directly with our enterprise customers and turn frontier AI capabilities into production-grade systems.

Responsibilities

• Embed within customer engineering teams and lead technical discovery sessions with business stakeholders, engineering leadership, and security to translate ambiguous business problems into clear AI architectures and delivery plans.
• Arcitect, code, and ship production-grade agentic AI solutions on Google Cloud — including multi-agent systems, MCP servers, sub-agents, skills, connectors, agentic wrappers, and safety guardrails — that move customers beyond pilots into measurable business value.
• Design and implement Retrieval-Augmented Generation (RAG) pipelines and grounding architectures, including chunking strategy, vector databases, and embedding optimization to prevent hallucinations and ensure response quality.
• Build the “connective tissue” between Google’s AI products and customer infrastructure, including APIs, legacy data silos, identity, and security perimeters.
• Implement multi-agent patterns such as ReAct, self-reflection, and hierarchical delegation using frameworks like Google’s Agent Development Kit (ADK) or LangGraph
• Build high-performance evaluation pipelines and observability frameworks for agentic systems, with attention to accuracy, safety, latency, cost-per-request, and tokens-per-second.
• Debug agent logic and optimize tool selection in live, high-traffic environments, including tracing conversation and request IDs across microservices to resolve production failures.
• Co-build with customer engineering teams and act as a hands-on advocate for AI-assisted development, introducing and operationalizing AI coding tools to accelerate delivery and elevate engineering practices.
• Drive a deliberate handoff to the customer’s team, ensuring long-term ownership, documentation, and end-user adoption after the engagement concludes.
• Develop and maintain technical documentation, architecture decision records, and evaluation results across all assigned engagements.

Qualifications

• Bachelor’s degree in Engineering, Computer Science, a related field, or equivalent practical experience.
• 5+ years of software development experience using Python, TypeScript, or comparable languages, with a track record of shipping production-grade code to external or internal customers.
• Hands-on experience architecting and deploying AI systems on Google Cloud Platform (GCP), including: Vertex AI — model deployment, fine-tuning workflows, evaluation, and platform-level observability. Gemini models — prompt engineering, structured outputs, function/tool calling, and multimodal use cases. BigQuery and Cloud Storage — as data and grounding sources for AI workloads. Cloud Run, Cloud Functions, and Pub/Sub — for deploying and orchestrating agentic services. Gemini Enterprise Agent Platform — designing, configuring, and deploying enterprise-grade agents, grounding on customer data sources, integrating tools and connectors.
• Demonstrated experience building agentic and AI-driven solutions in production, including: LLM application development — prompt engineering, agent development, and evaluation frameworks. RAG architectures — vector databases, chunking strategy, and retrieval evaluation. Data pipelines — structured and unstructured data ingestion to power enterprise-grade AI solutions. Experience deploying cloud resources via Terraform or similar infrastructure-as-code tools.
• Experience leading technical discovery sessions with business stakeholders and engineering teams to define AI requirements and translate ambiguous business goals into technical roadmaps.
• Experience integrating AI systems with enterprise IT infrastructure, including authenticated APIs, legacy data systems, and corporate security perimeters.
• Ability to travel up to 50% of the time to customer sites.

Nice to have

• Master’s degree or PhD in AI, Computer Science, Machine Learning, or a related technical field.
• Experience implementing multi-agent systems using frameworks such as Google’s Agent Development Kit (ADK), LangGraph, or CrewAI, and complex agent patterns including ReAct, self-reflection, and hierarchical delegation.
• Hands-on experience designing and deploying Model Context Protocol (MCP) servers, tool-calling protocols, and connector ecosystems for agentic systems.
• Knowledge of “LLM-native” operational metrics (tokens/sec, cost-per-request, time-to-first-token) and techniques for optimizing state management, granular tracing, and conversation-ID propagation across microservices.
• Track record of troubleshooting live, high-traffic production AI systems during critical windows.
• Experience architecting AI solutions within complex infrastructures, including data sovereignty, secure governance, and air-gapped or regulated environments.
• Experience designing user-facing interfaces for AI and agentic systems with attention to context engineering, transparency, and explainability.
• Experience driving organization-wide initiatives (e.g., migrations to new AI stacks, engineering-velocity programs) that deliver measurable improvements to engineering productivity and business outcomes.
• Experience as an advocate for AI-assisted software development, including introducing AI coding assistants to enterprise engineering teams and developing internal best practices for their use.
• Google Cloud certifications: Google Cloud Professional Machine Learning Engineer, Google Cloud Professional Cloud Architect, Google Cloud Professional Data Engineer.
• Familiarity with full-stack application development and REST/GraphQL API design.