AI Architect

We're looking for a highly skilled, build-oriented Forward Deployed Engineer (FDE) / Conversational AI Architect to engineer, assemble, and roll out advanced agentic AI platforms. This position has you functioning as the essential connector between leading-edge Generative AI models and sophisticated enterprise production systems. The work extends far past architectural planning; you'll produce production-quality code, manage multi-agent workflow orchestration via Gemini CX / Vertex AI Agent Builder, oversee deterministic state machines through Dialogflow CX, and develop secure cloud data pipelines leveraging the Advanced Agent Modeling (AAM) framework

Build and launch autonomous, outcome-focused multi-agent systems leveraging Gemini CX and Vertex AI Agent Studio, advancing customer interactions from basic deflection toward full end-to-end resolution Manage hybrid conversational pathways by merging generative playbooks with accurate state-machine oversight within Dialogflow CX, utilizing Pages, Parameters, Conditional Routing, and Transition Routes Develop, enhance, and maintain Retrieval-Augmented Generation (RAG) pipelines using Vertex AI Search, securely grounding agents in unstructured enterprise knowledge repositories Create and launch secure backend integrations, connectors, and webhooks through Cloud Run, Cloud Functions, and the Model Context Protocol (MCP), linking conversational systems to enterprise CRMs, ERPs, and internal databases Guarantee enterprise-grade security and regulatory adherence by deploying Model Armor constraints, setting up VPC Service Controls (VPC-SC), and enforcing strict IAM least-privilege policies Develop telemetry pipelines that transfer raw conversation transcripts from Dialogflow into BigQuery, using CCAI Insights to support large-scale error-taxonomy analysis, intent health checks, and containment rate measurement At least 5 years of relevant hands-on experience Minimum 2 years operating in Senior, Lead, Manager, or Owner-level positions Demonstrated success managing engagements for teams comprising 5+ full-time employees Substantial, practical experience throughout the Google Cloud AI ecosystem, covering Gemini CX, Google Cloud Contact Center AI (CCAI), and the Advanced Agent Modeling (AAM) framework Proven skill in conversation engineering, including Dialogflow CX, Speech-to-Text (STT) tuning (phrase hints, audio profiles), Text-to-Speech (TTS), and telephony/SIP trunking configuration Solid coding ability in Python or Node.js, where experience building custom automation scripts or working with Google Cloud wrapper libraries such as dfcx-scrapi stands as a strong bonus Dependable background with GCP infrastructure and DevOps resources, including Cloud Run, Cloud Functions, BigQuery, Looker Studio, and Infrastructure-as-Code practices via Terraform Working familiarity with cloud security concepts, data anonymization strategies, and isolating model training boundaries inside enterprise tenant restrictions Clear track record shifting generative AI agents from pilot/MVP status into fully scaled, live deployments reaching millions of users Fluent English communication skills at a B2 level or higher Holding a Google Cloud Professional Cloud Architect or Professional Data Engineer certification Having finished Google Cloud's official Agentic AI on Google Cloud or Gemini Enterprise for Customer Experience (GECX) training paths Background rolling out large-scale customer service solutions in Financial Services, Telecom, Retail, or Healthcare domains