Note: The job is a remote job and is open to candidates in USA. UnivEdge Consulting is hiring an Agentic AI Engineer to build governed AI agents that operate against live cloud infrastructure. The role focuses on developing agent workflows for infrastructure analysis, Infrastructure-as-Code generation and validation, controlled remediation and provisioning, integrations with observability and ITSM systems, and deployment through CI/CD pipelines.
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
Skills
- • 2+ 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 design
- • RAG fundamentals: embeddings, vector stores (pgvector, OpenSearch, Pinecone), retrieval quality tuning
- • Agent evaluation and observability (LangSmith, Langfuse, Ragas, or equivalent custom harnesses)
- • 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 design
- • CI/CD: GitHub Actions, Azure DevOps, GitLab CI or Jenkins
- • Containers and orchestration (Docker, Kubernetes)
- • Expert-level Python (async, API integration, testing)
- • Secrets management (Vault, AWS Secrets Manager, Azure Key Vault)
- • Git-based workflows and code review discipline
- • Observability tooling - DataDog strongly preferred
Benefits
- US, Remote
Company Overview