AI Platform Operations Engineer

Role Summary

Key Responsibilities

• Operate Azure AI Foundry, Azure OpenAI, and associated Azure AI platform services.
• Support onboarding of Nexus AI, Generative AI, and agentic workloads using approved landing zones, blueprints, governance gates, and release processes.
• Support AI gateway and API Management exposure, including API connectivity, registration, and production-readiness checks.
• Assist teams with environment readiness, identity and access, network and API connectivity, deployment checks, and post-deployment verification.
• Apply guardrails, content safety controls, observability, quota controls, cost attribution, and use-case governance to AI workloads.
• Support prompt and model monitoring, evaluations, dashboards, alerts, and operational health indicators.
• Support integrations with MCP and agent interfaces, data products, event streams, and operational data stores.
• Track incidents, onboarding issues, risks, and dependencies and coordinate resolution across technical teams.
• Maintain onboarding checklists, operational procedures, troubleshooting guides, governance evidence, and handover materials.

Must-Have Skills

• Minimum three years of hands-on Microsoft Azure experience is required.
• Strong experience with Azure AI Foundry, Azure OpenAI, and Azure AI Services is required.
• Experience with Azure API Management and API exposure patterns is required.
• Knowledge of Generative AI, Large Language Models, RAG, and Agentic AI concepts is required.
• Experience implementing AI guardrails, content filtering, and Responsible AI controls is required.
• Familiarity with AI observability, monitoring, logging, and performance tracking is required.
• Experience with Azure Monitor, Application Insights, Log Analytics, and Azure Cost Management is required.
• Understanding of Azure security, RBAC, Managed Identities, Key Vault, and networking is required.
• Strong troubleshooting, operational support, and stakeholder management skills are required.

Preferred Skills

• Experience with AI Gateway solutions such as Azure APIM AI Gateway is preferred.
• Knowledge of Prompt Flow, AI evaluations, and model benchmarking frameworks is preferred.
• Experience with LangChain, LangGraph, Semantic Kernel, or AutoGen is preferred.
• Exposure to MLOps, CI/CD pipelines, GitHub Actions, and Azure DevOps is preferred.
• Knowledge of Microsoft Purview, AI governance, and compliance frameworks is preferred.
• Experience with vector databases, Azure AI Search, and RAG architectures is preferred.
• Familiarity with Kubernetes, Container Apps, or enterprise-scale Azure OpenAI is preferred.
• Knowledge of quota planning, token consumption analysis, and FinOps practices is preferred.

Required Experience and Skills

• Three to ten years of Azure administration or operations experience, including production cloud support, is required.
• Operational knowledge of Azure AI Foundry, Azure OpenAI, Generative AI workload patterns, and agentic application operations is required.
• Understanding of AI gateway or APIM, REST APIs, MCP, guardrails, content safety, prompt and model monitoring, and evaluation concepts is required.
• Working knowledge of identity, managed identities, RBAC, secrets management, private connectivity, security controls, quota management, and cost attribution is required.
• Operational familiarity with APIM, Azure Event Hubs, Application Insights, Cosmos DB, and ADLS Gen2 is required.
• Strong incident and problem management, stakeholder coordination, runbook preparation, and knowledge-transfer skills are required.

Preferred Certifications

• Microsoft Azure Administrator Associate certification is strongly preferred.
• Azure AI Engineer Associate and Azure Solutions Architect Expert certifications are preferred.
• Google Cloud Associate Cloud Engineer certification is advantageous due to cross-cloud dependencies.

Key Deliverables