Design, build, and deploy GenAI solutions on Azure using Azure OpenAI, AI Foundry, and Python, following enterprise security and governance standards. 

Implement Retrieval-Augmented Generation (RAG) architectures: document ingestion, chunking, embeddings, vector indexing, retrieval strategies, and response generation with citations/grounding. 

Design and optimize Azure AI Search (keyword + vector + hybrid) indices, skillsets, and enrichment pipelines to improve retrieval quality and latency. 

Develop prompt engineering patterns, tool/function calling, and agentic orchestration workflows using Azure cloud-native frameworks such as Semantic Kernel, Azure AI Foundry (Agents/Agent Service) and Prompt Flow, with strong evaluation, safety, and fallback strategies. 

Integrate AI solutions with Azure services such as Azure Functions, App Service/Container Apps, AKS, API Management, Event Grid/Service Bus, Storage, Key Vault, and Azure Monitor. 

Implement LLMOps/MLOps practices: CI/CD for prompts/models, environment promotion, model/prompt versioning, automated evaluation, and monitoring for drift, cost, and quality. 

Build data pipelines for unstructured and structured data, including extraction, normalization, metadata management, and access controls for enterprise knowledge bases. 

Apply Responsible AI practices: content filtering, prompt injection defenses, PII handling, data residency considerations, and human-in-the-loop review where needed. 

Estimate and manage Azure AI solution costs (token usage, search queries, storage, compute) and optimize performance through caching, batching, and retrieval tuning. 

Collaborate with stakeholders to translate business problems into AI use cases, define success metrics, and deliver production-ready solutions. 

Perform code reviews and establish engineering standards for Python services, API design, testing, security, and reliability for AI applications. 

Maintain clear documentation for architecture, prompts, evaluation results, data sources, and operational runbooks; support incident triage and continuous improvements. 

10+ years of overall experience with strong recent hands-on delivery of AI/ML and GenAI solutions on Microsoft Azure. 

Strong expertise in Retrieval-Augmented Generation (RAG) patterns, embeddings, vector databases/indexes, and evaluation of retrieval + generation quality. 

Hands-on with Azure AI Search including vector/hybrid search, semantic ranking, index design, skillsets/enrichment, and performance tuning. 

Hands-on with Azure OpenAI (chat/completions, embeddings, function calling/tools) and AI Foundry for building, evaluating, and operationalizing GenAI apps. 

Hands-on experience with Azure cloud-native agentic frameworks and tooling such as Semantic Kernel, Azure AI Foundry (Agents/Agent Service) and Prompt Flow to build orchestrated, tool-using AI applications. 

Understanding of MCP (Model Context Protocol) and how it applies to integrating tools/connectors, managing context, and enabling interoperable agent workflows in enterprise GenAI solutions. 

Strong Python engineering skills (FastAPI/Flask preferred), with experience building REST APIs and integrating with enterprise systems. 

Experience with Azure AI services and data components such as Azure AI Services (Cognitive Services), Azure Machine Learning, Data Factory/Synapse, Blob/ADLS, and Cosmos DB (as applicable). 

Experience implementing CI/CD and LLMOps/MLOps using Azure DevOps or GitHub Actions, with automated tests, evaluations, and deployment pipelines. 

Good knowledge of Azure security and governance: Entra ID, Managed Identities, Key Vault, network isolation/private endpoints, RBAC, logging/monitoring, and compliance considerations. 

Strong troubleshooting and analytical skills; ability to diagnose retrieval quality issues, hallucinations, latency bottlenecks, and production incidents. 

Excellent communication and stakeholder management; ability to explain AI concepts, risks, and trade-offs to technical and non-technical audiences.