AI Automation Engineer II

About the role

Our client is seeking an innovative AI Automation Engineer II to help build and scale a next-generation Enterprise Operational AI Platform. This is a highly technical, hands-on engineering role focused on AI architecture, data integrations, and multi-agent orchestration that will transform how IT Operations teams access data, resolve incidents, and automate support functions.

As a key member of the team, you will partner with senior AI architects to develop a centralized AI interface that provides Infrastructure & Operations (I&O) engineers with real-time operational insights, automated workflows, and intelligent decision support. Your work will directly influence initiatives including:

AI-powered Help Desk automation.

Incident triage and root cause analysis (RCA).

Infrastructure intelligence and observability.

Autonomous remediation and self-healing operations.

Enterprise-wide operational data integration.

This is an opportunity to work at the intersection of Generative AI, LLMs, multi-agent systems, AIOps, and enterprise infrastructure.

About the Platform:

The Enterprise Operational AI Platform serves as the single entry point for IT Operations teams to access operational data, automation capabilities, and infrastructure intelligence across the organization.

The platform is built around a multi-agent AI architecture powered by advanced LLMs and integrates with critical enterprise systems including:

ServiceNow

Dynatrace

Zabbix

Google Cloud Platform (GCP)

Enterprise search platforms (such as Glean)

Using technologies such as Model Context Protocol (MCP) and agentic AI frameworks, the platform enables everything from read-only operational insights to fully autonomous remediation and proactive outage prevention.

Responsibilities:

AI Platform Development

Develop and enhance a centralized AI assistant for IT Operations teams.

Design, build, and maintain multi-agent AI workflows and orchestration frameworks.

Implement Model Context Protocol (MCP) integrations for real-time operational tasks.

Build AI-driven workflows supporting incident management, infrastructure discovery, capacity planning, and outage prevention.

Enterprise Data Integration

Design and develop scalable integrations with ServiceNow, Dynatrace, Zabbix, GCP, CMDBs, and other infrastructure data sources.

Enable ingestion, contextualization, and reasoning across operational datasets.

Partner with observability and enterprise search teams to improve AI accuracy and reduce hallucinations.

Leverage AI-assisted development tools such as Devin and Windsurf to accelerate engineering delivery.

Use Case Delivery & Automation

Deliver AI-powered Help Desk and Incident Management solutions.

Build intelligent workflows for maintenance suppression, change management, and operational automation.

Support the evolution from AI-assisted recommendations to autonomous remediation capabilities.

Develop metrics and observability frameworks to measure AI performance, confidence, adoption, and MTTR improvements.

Required Skills and Expertise:

Large Language Models (LLMs).

Agentic AI frameworks.

Prompt engineering.

Retrieval-Augmented Generation (RAG).

AI orchestration platforms.

3-5 years of overall engineering experience, including a foundation in one or more of:

Python development.

Backend software engineering.

API development and integration.

Data engineering.

AIOps or IT automation.

Experience building or integrating AI agents, automated workflows, or orchestration frameworks.

Knowledge of Model Context Protocol (MCP) or similar integration frameworks is strongly preferred.

Understanding of AI observability, monitoring, and governance best practices.

Experience integrating with or supporting enterprise IT platforms such as:

ServiceNow

Dynatrace

Zabbix

GCP

CMDB platforms

Monitoring and observability tools

Preferred Skills and Expertise:

Experience with autonomous AI agents and multi-agent systems.

Familiarity with Devin, Windsurf, or other AI-assisted development platforms.

Experience implementing operational AI or AIOps solutions.

Knowledge of incident management, problem management, and root cause analysis processes.

Experience building AI solutions within large-scale enterprise environments.