EngineerJobs.io
← Back to all jobs

Job Description

Robotics Technologies is hiring an Agentic AI Engineer to design and deliver AI agents that can operate safely against live cloud infrastructure. This contract role is focused on governed automation that interprets infrastructure state and telemetry, generates Infrastructure-as-Code, and performs controlled remediation or provisioning with human-in-the-loop approval.

The engagement emphasizes deploying working automation into a real environment within the project window, with clear guardrails, auditability, and a handoff to the client’s platform team at close.

What you’ll do

  • Build and deploy agentic workflows using an LLM orchestration framework such as LangGraph, CrewAI, AutoGen, Semantic Kernel, or cloud-native equivalents like Bedrock Agents and Azure AI Agent Service.
  • Create tool and function-calling layers that safely expose infrastructure operations to agents, including MCP-based tooling where applicable.
  • Programmatically generate, review, and validate Terraform modules, integrating policy checks into agent output paths using OPA/Sentinel as well as tflint and checkov.
  • Connect agent workflows with observability and ITSM systems for alert triage and automated ticket-to-action flows across DataDog, ServiceNow, PagerDuty, and Jira.
  • Implement agent guardrails including least-privilege execution roles, approval gates, and dry-run/plan-only modes, along with audit logging for every agent action.
  • Develop evaluation and regression harnesses to measure agent behavior, including accuracy, tool-selection correctness, and failure containment.
  • Integrate agent workflows into existing CI/CD pipelines.
  • Document the architecture and complete a platform-team handover at engagement close.

What you bring

  • 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) with experience in tool/function calling and structured outputs.
  • Practical experience designing agent guardrails, retries, failure handling, and human-in-the-loop approval.
  • RAG fundamentals, including embeddings, vector stores such as pgvector, OpenSearch, or Pinecone, and retrieval quality tuning.
  • Agent evaluation and observability using LangSmith, Langfuse, Ragas, or equivalent custom harnesses.
  • 5+ years in cloud infrastructure, platform, or DevOps engineering.
  • Deep Terraform knowledge including module design, state and remote backends, workspaces, and drift handling (with Terragrunt or Terraform Cloud/Enterprise as a plus).
  • Policy-as-code experience with OPA/Rego, Sentinel, or equivalents.
  • Cloud depth in at least one of AWS, Azure, or OCI, including IAM and least-privilege design.
  • CI/CD experience with GitHub Actions, Azure DevOps, GitLab CI, or Jenkins.
  • Containers and orchestration experience with Docker and Kubernetes.
  • DataDog is strongly preferred for observability.
  • Expert-level Python (async, API integration, testing).
  • Secrets management experience with Vault, AWS Secrets Manager, or Azure Key Vault.
  • Experience with Git-based workflows and code review discipline.

Tools and technologies you may use

  • Agent/orchestration: LangGraph, CrewAI, AutoGen, Semantic Kernel, Bedrock Agents, Azure AI Agent Service, MCP
  • Infrastructure and policy: Terraform, OPA, Sentinel, tflint, checkov, Terragrunt, Terraform Cloud/Enterprise
  • Observability and ITSM: DataDog, ServiceNow, PagerDuty, Jira
  • Evaluation: LangSmith, Langfuse, Ragas
  • Cloud and platform: AWS, Azure, OCI, IAM, Docker, Kubernetes
  • CI/CD: GitHub Actions, Azure DevOps, GitLab CI, Jenkins
  • Data/RAG: Python, pgvector, OpenSearch, Pinecone
  • Secrets: Vault, AWS Secrets Manager, Azure Key Vault

Nice to have

  • Prior experience building agents that take write actions against production infrastructure.
  • Model Context Protocol (MCP) server/client implementation.
  • Exposure to FinOps tooling such as Cloudability or Apptio.
  • Oracle Cloud Infrastructure (OCI) experience.
  • Healthcare or other regulated-industry experience.

Location: Weehawken, NJ (onsite)

Compensation: USD 84 per hour

Job type: Contract

Similar Jobs