Description

Architect and operate agentic AI services and microservices on Azure, managing CI/CD pipelines, infrastructure as code, and enterprise-grade observability.

This role is remote.

Responsibilities

• Architect, build, and operate agentic AI services using LangChain, LangSmith, OpenAI/Azure OpenAI, and LiteLLM, implementing tool-use orchestration and guardrails.
• Design and maintain CI/CD pipelines via Azure DevOps (ADO) YAML and GitHub Actions, enforcing trunk-based workflows and automated rollbacks.
• Manage Azure infrastructure (AKS, Service Bus, Event Hubs, Key Vault) using Terraform, ensuring secure networking and RBAC.
• Operate Kubernetes with CNI networking and Linkerd service mesh, implementing canary/blue-green strategies and autoscaling.
• Create Apache NiFi dataflows and deploy clusters on AKS; implement observability using ELK/EFK, Prometheus, and KQL-based alerting.

Required Skills

• 12+ years of DevOps experience with expert-level hands-on skills in Azure and Kubernetes.
• Proficiency with Azure DevOps (ADO) YAML pipelines and GitHub Actions for cloud-native systems.
• Strong Kubernetes operations including CNI networking, service mesh (Linkerd), and container build (Docker, Buildah).
• Experience with ELK/EFK, Prometheus, Fluentd/Fluent Bit, and Azure Monitor dashboards for observability at scale.
• Deep automation skills with PowerShell, Bash, and Python to eliminate toil across build and release workflows.
• Infrastructure as Code expertise with Terraform for Azure resources.
• Practical production experience delivering agentic AI solutions using LangChain, LangSmith, and LLM observability tools.

Preferred Skills

• Apache NiFi expertise for authoring and governing dataflows on AKS.
• Experience with data/analytics integrations including Azure Databricks, Snowflake, and Power BI.
• Networking fundamentals including DHCP/DNS and load balancer configuration (NGINX, HAProxy).

Key Skills

Education

Bachelor's degree