Technical Specialist (IN)
HCLTech
HCLTech
Seeking a Senior Technical Specialist to be the primary subject-matter expert for the operational excellence, observability, and lifecycle management of AI agents in production environments. This role focuses on establishing and maintaining robust frameworks and practices for the safe deployment, continuous monitoring, effective evaluation, and ongoing improvement of live agents. The goal is to ensure optimal reliability, safety, cost-efficiency, and achievement of key business performance indicators across the Intel Agent Factory.
This is a crucial role for driving the efficiency and effectiveness of our AI agent deployments, requiring deep technical expertise and a strategic approach to operations.
Define and implement the AgenticOps framework, encompassing agent registry, version control, guarded rollout strategies, and rollback procedures for production agents.
Establish comprehensive continuous evaluation and monitoring systems for agent quality, autonomy, safety (including guardrails and Model Armor), latency, cost, and reuse metrics.
Implement advanced observability and tracing solutions for complex multi-agent systems, leveraging tools like Agent Engine Observability and Cloud Monitoring/Logging/Trace.
Own the end-to-end 5-gate validation-to-production process and manage post-release escape events for deployed agents.
Design and oversee human-in-the-loop (HITL) supervision mechanisms, feedback loops, and automated pre-production simulations to ensure safe and controlled rollouts.
Track and report on key agent business KPIs such as CSAT, TAT, MTTR, and cost savings through dedicated AgentScore / Agent 360 dashboards.
Drive cost governance initiatives for agent runtimes, including model tiering, context caching, batch/flex inference optimization, and the implementation of budget caps and alerts.
Collaborate closely with DevOps and AI & Data SMEs to seamlessly integrate the build-deploy-operate-improve cycle, providing guidance on AgenticOps ownership transfer to Intel.
Extensive experience in LLMOps, MLOps, or AgentOps, with a proven track record of operating GenAI or agentic systems in production.
Hands-on expertise with Google Cloud agent runtimes, specifically Vertex AI and Agent Engine, along with their associated observability tooling.
Proficiency in agent evaluation and safety practices, including eval frameworks, guardrails, Model Armor, HITL, prompt engineering, and robustness testing.
Strong background in monitoring, tracing, and reliability engineering (SRE) for AI workloads.
Demonstrated ability in cost governance and performance tuning for LLM/agent workloads.
High proficiency in Python and a solid understanding of the agent lifecycle and governance principles.
Additional experience with ADK, A2A, MCP, and multi-agent orchestration in production environments is beneficial.
Familiarity with BigQuery/Looker for agent analytics and KPI dashboard creation.
Knowledge of Responsible AI principles, model governance, and audit/compliance frameworks.
Prior experience with enterprise-scale AI platform operations.
A minimum of 9-12+ years in ML/AI platform operations, SRE, or LLMOps, with exposure to production agentic/GenAI systems (Tier 5–6).
A Google Cloud Professional (ML/DevOps) certification is preferred.
Availability for offshore (India) work with US overlap, or onsite (USA) work as required.
HCLTech
IT Consulting