Skip to main content

Agentic AI Engineer - Cloud Infrastructure Automation

Posted today

acestackDenver (CO)

SENIORITY

Lead

Apply (opens in a new tab)

About the role

Role: Agentic AI Engineer - Cloud Infrastructure Automation
Location: US, Remote
ContractRole Summary We are seeking an Agentic AI Engineer to design and deliver AI agents that operate against live cloud infrastructure. This is a hands-on build role: you will stand up agent workflows that interpret infrastructure state and telemetry, generate and validate Infrastructure-as-Code, and execute controlled remediation and provisioning actions under human-in-the-loop approval. This is not a research or prototyping role. The expectation is working, governed automation deployed into a real environment within the engagement window.
Key Responsibilities:
  • Build and deploy agentic workflows using an LLM orchestration framework (LangGraph, CrewAI, AutoGen, Semantic Kernel, or cloud-native equivalents such as Bedrock Agents / Azure AI Agent Service)
  • Design and implement tool/function-calling layers that expose infrastructure operations to agents safely - including MCP-based tooling where applicable
  • Generate, review and validate Terraform modules programmatically; integrate policy-as-code checks (OPA/Sentinel, tflint, checkov) into agent output paths
  • Integrate agents with observability and ITSM systems (DataDog, ServiceNow, PagerDuty, Jira) for alert triage and automated ticket-to-action flows
  • Implement guardrails: least-privilege execution roles, approval gates, dry-run/plan-only modes, audit logging of every agent action
  • Build evaluation and regression harnesses for agent behaviour (accuracy, tool-selection correctness, failure containment)
  • Wire agent workflows into existing CI/CD pipelines
  • Document architecture and hand over to the client's platform team at engagement close
Required Skills:
  • Agentic AI / LLM2+ years building production LLM applications, including at least one deployed multi-step agentic system
  • Strong command of one orchestration framework (LangGraph/LangChain, CrewAI, AutoGen, Semantic Kernel) plus tool/function calling and structured output
  • Practical experience with agent guardrails, retries, failure handling and human-in-the-loop approval designRAG fundamentals: embeddings, vector stores (pgvector, OpenSearch, Pinecone), retrieval quality tuning
  • Agent evaluation and observability (LangSmith, Langfuse, Ragas, or equivalent custom harnesses)
  • Infrastructure / Platform 5+ years in cloud infrastructure, platform or DevOps engineering
  • Deep Terraform: module design, state and remote backends, workspaces, drift handling; Terragrunt or Terraform Cloud/Enterprise a plus
  • Policy-as-code: OPA/Rego, Sentinel, or equivalent
  • Cloud depth in at least one of AWS / Azure / OCI, including IAM and least-privilege designCI/CD: GitHub Actions, Azure DevOps, GitLab CI or Jenkins
  • Containers and orchestration (Docker, Kubernetes)
  • Observability tooling - DataDog strongly preferred
  • EngineeringExpert-level Python (async, API integration, testing)
  • Secrets management (Vault, AWS Secrets Manager, Azure Key Vault)
  • Git-based workflows and code review discipline
Nice to Have:
  • Prior experience building agents that take write actions against production infrastructure
  • Model Context Protocol (MCP) server/client implementation
  • FinOps tooling exposure (Cloudability, Apptio)
  • Oracle Cloud Infrastructure (OCI)
  • Healthcare or regulated-industry environment experience

Before you apply

Applying takes about a minute. These four things decide how fast it moves after that.

Your profile is current

It's what we read first. Occupations, seniority and locations matter more than a long history.

Two examples you can talk through

Not a portfolio — just two pieces of work where you can explain the decisions and what you'd change.

A number in mind

What you're on now and what would make you move. We negotiate better when we know both.

Your notice period

Employers plan around it, and it's the question that stalls offers most often.

Once you apply, someone reads it and calls you before anything reaches the employer — usually within two working days.

More like this