AI Automation Infrastructure Engineer

NICE • Sandy, UT

7h

About The Position

We’re looking for an AI Engineer with strong expertise in Voice, Network, and Compute infrastructure automation. You will design and deploy AI‑driven automation that improves reliability, performance, and operational efficiency across large‑scale systems. This role emphasizes agent‑based automation, MCP‑style service frameworks, and reusable Skills that enable intelligent workflows across infrastructure platforms.

Requirements

• 5+ years of experience in AI/ML engineering, automation engineering, or infrastructure engineering.
• Strong Python development skills, including API and service development.
• Hands‑on experience with: Voice: SIP, SBCs, call flows Network: routing/switching, F5, Palo Alto, Arista Compute: VMware, Kubernetes, and cloud platforms
• Experience building or operating MCP‑like services, agent backends, or tool‑calling frameworks that allow LLMs to interact with real systems.
• Proven ability to create modular Skills or tools for workflow automation and agent execution.
• Experience with ML frameworks and LLM orchestration tools.
• Solid understanding of CI/CD, GitOps, containers, and orchestration.

Nice To Haves

• Cloud‑native automation experience (AWS Lambda, Azure Functions, GCP Cloud Functions).
• Knowledge of Kafka or other event/streaming frameworks.
• Experience with policy engines, RBAC, and safety controls for AI automation.
• Networking, cloud, or automation certifications.

Responsibilities

• Build AI/ML‑powered automation for Voice, Network, and Compute platforms.
• Design and deploy Model Context Protocol (MCP)–style servers or similar agent service layers that expose infrastructure capabilities as secure, reusable AI‑callable actions.
• Develop Skills and tools for workflow automation, enabling LLM‑driven agents to execute operational tasks, diagnostics, and remediation safely and deterministically.
• Create intelligent systems for anomaly detection, forecasting, root cause analysis, and self‑healing.
• Integrate automation with SBCs, SIP systems, routers/switches, load balancers (F5, Palo Alto, Arista), VMware, Kubernetes, and cloud compute platforms.
• Build APIs, Skills, and agent workflows that connect with observability, CMDB, and ticketing platforms (Grafana, Prometheus, ServiceNow, etc.).
• Implement Infrastructure‑as‑Code using Terraform, Ansible, or similar tools.
• Partner with operations teams to eliminate manual work, improve uptime, and accelerate incident response.
• Define guardrails, permissions, and validation layers to ensure AI‑driven automation operates safely in production environments.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: No Education Listed
• Number of Employees: 1,001-5,000 employees