Job Title: Cyber Security - Microsoft Foundry
JOB SUMMARY
The role involves designing and implementing GenAI and agentic architectures on Azure AI Foundry, integrating AI solutions with data platforms, and ensuring responsible AI, security, and operational practices.
Key Responsibilities
• Design end-to-end GenAI and agentic architectures on Azure AI Foundry model selection, agents, tools, retrieval, evaluation, and deployment
• Define multi-agent patterns: planner-executor, supervisor, handoff, human-in-the-loop using Foundry Agent Service, Semantic Kernel, LangGraph
• Architect RAG and knowledge grounding with Azure AI Search vector indexes and Databricks Vector Search over governed data
• Integrate agents with enterprise systems through Model Context Protocol (MCP), OpenAPI tools, Azure Functions, Logic Apps, and API Management
• Connect AI solutions to the lakehouse: Databricks Unity Catalog, Delta Lake, feature and vector stores, and Microsoft Fabric/OneLake where present
• Shape data products and semantic layers that agents can reliably reason over
• Design LLMOps/MLOps pipelines with MLflow, Foundry evaluations, prompt versioning, and CI/CD in Azure DevOps or GitHub Actions
• Build in guardrails: Azure AI Content Safety, prompt-injection defenses, PII redaction, and grounded-answer checks
• Apply Entra ID, managed identities, private networking, Key Vault, and Defender for Cloud to every design
• Set up observability, tracing, cost controls, and token budgeting with Azure Monitor and Application Insights
• Map solutions to regulatory needs: NAIC AI model bulletin, NYDFS Part 500, SOC 2, and model risk management
Required Qualifications
• Hands-on production experience with Azure AI Foundry: Projects and hubs, model catalog, Foundry Agent Service, prompt flow, evaluations, tracing, content safety
• Hands-on production experience with Azure OpenAI and models: GPT-family and open models, function calling, structured outputs, finetuning basics, token and cost management
• Hands-on experience with Agentic AI: Multi-agent orchestration, tool use, memory, planning, MCP, A2A patterns, Semantic Kernel, AutoGen, LangGraph or similar
• Hands-on experience with RAG and search: Azure AI Search, hybrid semantic ranker, chunking and embedding strategy, retrieval evaluation
• Architect-level experience with Azure platform: AKS, Container Apps, Functions, API Management, Event Grid, Service Bus, Cosmos DB
• Architect-level experience with Security and identity: Entra ID, managed identity, private endpoints, VNet, Key Vault, RBAC
• Knowledge and some experience on MLFlow Mosaic
• Hands-on experience with Engineering: Python required, REST APIs, IaC with Bicep or Terraform, CI/CD
• 10 years in software, data, or cloud architecture, including 3 years on Azure at architect level
• Experience in building GenAI/LLM solutions with at least one agentic system in production or latest-stage pilot
• 1-2 years working with Databricks on Azure
• Client-facing consulting or solution architecture experience in a services firm or large enterprise
Preferred Qualifications
• Experience with Databricks: Lakehouse on Azure, Databricks Unity Catalog, Delta Lake, MLflow, Mosaic AI, Vector Search, model serving
• Nice to have: Apply Entra ID, managed identities, private networking, Key Vault, and Defender for Cloud to every design
• Nice to have: Map solutions to regulatory needs: NAIC AI model bulletin, NYDFS Part 500, SOC 2, and model risk management