AgenticOps SME

Agentic Ops SME LLMOps / MLOps / GCP
Santa Clara, CA
Role Summary

• Senior Agentic Ops / LLMOps / MLOps Subject Matter Expert responsible for operating, monitoring, and continuously improving production AI agents.
• Own the Agentic Ops framework across the AI Agent Factory, ensuring reliability, safety, observability, cost efficiency, governance, and business KPI performance
  .
• Lead the complete agent lifecycle from validation and deployment through production monitoring, evaluation, optimization, and continuous improvement.

• Define and operate Agentic Ops frameworks covering agent registry, versioning, controlled rollouts, rollback, and lifecycle governance
  .
• Establish continuous evaluation and monitoring for quality, autonomy, safety, latency, cost, reuse, and reliability
  .
• Implement observability and distributed tracing for multi-agent systems using Google Cloud Agent Engine, Cloud Monitoring, Cloud Logging, and Cloud Trace
  .
• Own the validation-to-production gate process and manage post-production issues and escape remediation.
• Design Human-in-the-Loop (HITL) supervision, feedback mechanisms, and automated pre-production simulations.
• Track agent business KPIs such as CSAT, TAT, MTTR, cost savings, and operational performance through dashboards and analytics.
• Drive LLM/agent cost optimization through model tiering, context caching, batch/flex inference, budget controls, and cost alerts
  .
• Partner with Dev Ops, AI, and Data teams to establish an effective build deploy operate improve lifecycle.
• Provide technical guidance on Agentic Ops operating models, ownership transition, governance, and enterprise adoption.

• Strong hands‑on experience with LLMOps, MLOps, Agent Ops, or AI platform operations in production.
• Extensive experience operating GenAI and agentic AI systems in enterprise environments.
• Hands‑on expertise with Google Cloud Vertex AI, Agent Engine, and GCP observability tools
  .
• Strong knowledge of AI/agent evaluation frameworks, guardrails, Model Armor, HITL, prompt testing, and robustness testing
  .
• Experience with monitoring, distributed tracing, reliability engineering, and SRE practices for AI workloads
  .
• Strong understanding of LLM/agent performance and cost optimization
  .
• Proficiency in Python
  .
• Strong understanding of agent lifecycle management, governance, reliability, and production operations.

• Experience with ADK, A2A, MCP, and multi‑agent orchestration in production.
• Experience using Big Query and Looker for agent analytics and KPI reporting.
• Knowledge of Responsible AI, model governance, audit, compliance, and AI risk frameworks
  .
• Experience supporting enterprise‑scale AI/ML platforms
  .

• 9 12+ years of experience in ML/AI platform operations, SRE, MLOps, or LLMOps, with significant production GenAI/agentic AI experience.
• Google Cloud Professional certification in Machine Learning, Dev Ops, or a related discipline is preferred.