About the role
Requirements:
- Experience: 5 - 10 years.
- Strong hands-on experience in the Microsoft Azure cloud.
- Good understanding of Azure services such as Compute, Storage, Event Hub, Event Subscription, Storage Queue, and PaaS services.
- Basic understanding of Azure AI Foundry and AI-related Azure service setup.
- Good Azure networking basics: VNet, subnet, routing, and basic troubleshooting.
- Strong knowledge of Terraform, especially Terraform state plan / apply troubleshooting failures migration risks Terraform Enterprise concepts.
- Strong Python coding capability, not just basic scripting.
- Experience using Python for API integration, automation, JSON/YAML handling, and internal tooling.
- Good understanding of CI/CD pipelines.
- Ability to troubleshoot pipeline failures.
- Comfortable with YAML and JSON. Ability to troubleshoot Azure infrastructure/platform issues.
- Ability to collect logs/evidence and coordinate with network/app/Microsoft support teams.
- Basic awareness of agentic AI / LLM concepts.
- Awareness of security and cost best practices.
Good to Have Skills:
- Hands-on experience with Harness. Hands-on experience with Terraform Enterprise.
- Exposure to LangGraph / LangChain. Exposure to agentic AI workflows or skill creation.
- Exposure to Claude or enterprise LLM integrations.
- Knowledge of Azure ML Workspace, model registry, and managed endpoints.
- MLOps / LLMOps knowledge. FinOps/azure cost optimization experience.
- Azure certifications: AZ-104, AZ-305, AZ-400, AZ-500