AI Ops Engineer

Role Overview We are seeking an AI Ops Engineer Production Support to maintain and support AI-powered customer service systems built on Google Cloud Contact Center AI (CCAI) and Generative AI technologies. This role focuses on operational stability, monitoring, incident resolution, and performance optimization for conversational AI platforms including Dialogflow CX virtual agents, Agent Assist, and LLM-powered assistants. You will work closely with AI engineering, DevOps, and contact center teams to ensure high availability and reliable performance of AI-driven customer engagement solutions. Key ResponsibilitiesProduction Support & Operations Provide L2/L3 production support for AI-driven contact center solutions. Monitor health and availability of CCAI services, Dialogflow CX agents, and GenAI applications. Investigate and resolve production incidents, failures, and performance issues. Monitoring & Observability Monitor AI system performance using: Google Cloud Monitoring Cloud Logging BigQuery analytics Track key metrics such as: Intent recognition accuracy Conversation containment rate LLM response latency Escalation to human agents Incident Management Perform root cause analysis (RCA) for production issues. Coordinate with engineering teams to implement fixes and improvements. Maintain incident documentation and operational runbooks. AI System Maintenance Support updates and releases for: Dialogflow CX conversational flows Prompt templates Knowledge bases and RAG pipelines Validate deployments and ensure production stability. Integration Support Troubleshoot integrations between AI systems and enterprise platforms such as: CRM systems Knowledge bases Ticketing platforms Backend APIs and webhooks Required Skills Experience supporting Google Cloud Platform (GCP) environments. Hands-on experience with Google Cloud Contact Center AI (CCAI) or Dialogflow CX. Understanding of Generative AI / LLM-based applications. Proficiency in Python, Node.js, or similar scripting languages. Experience with REST APIs, webhooks, and system integrations. Familiarity with monitoring, logging, and incident management processes….