• Design, build, and deploy AI solutions using Microsoft Azure, Azure AI Foundry, AWS
• Develop and manage LLM-based applications using Azure OpenAI and related services
• Implement agent-based architectures, including orchestration, tool-calling, and multi-step workflows
• Build production-ready AI pipelines with proper logging, monitoring, evaluation, and versioning
• Integrate AI services with enterprise systems via APIs, event-driven patterns, and data platforms
• Configure and manage model deployments, prompt flows, evaluations, and safety controls in AI Foundry
• Ensure solutions meet enterprise requirements for security, privacy, and compliance
• Optimize for latency, cost, scalability, and reliability
• Collaborate with architecture, security, DevOps, and product teams to move from POC to production
• Contribute to reusable AI patterns, internal frameworks, and best practices

Requirements:

• Strong hands-on experience with Azure OpenAI (model deployments, scaling, quota management)
• Understanding of Azure AI Foundry: Prompt flows, Evaluations, Model management, Safety configurations, Deployment pipelines
• Experience building AI agents and tool-calling systems
• Understanding of MCP concepts and secure tool integration patterns
• Experience with orchestration frameworks such as Semantic Kernel, LangChain, or similar
• Knowledge of RAG architectures, embedding pipelines, and vector search
• Experience implementing human-in-the-loop patterns