Microsoft Foundry SME

Role Summary

Avanade India's Artificial Intelligence practice is looking for a Microsoft Foundry SME to be a deep technical specialist on generative AI and agentic AI projects built on Microsoft Foundry. This is a hands-on, individual-contributor role for someone who wants to own the technical build — designing and implementing AI components, solving complex implementation challenges, and providing specialist guidance to the wider delivery team.

Key Responsibilities

• Design and build components of Microsoft Foundry solutions: model catalog integration, prompt flow/orchestration, agent design, and RAG pipelines (Azure AI Search, vector indexing, grounding data).
• Implement multi-agent orchestration patterns using frameworks such as Semantic Kernel, AutoGen, or LangChain/LangGraph.
• Act as the technical specialist/go-to resource on Microsoft Foundry within project teams, resolving complex implementation issues and edge cases.
• Support the Microsoft Foundry Lead/Architect in solution design, technical estimation, and implementation planning.
• Write and review production-quality code; ensure adherence to engineering best practices, testing, and CI/CD standards.
• Apply Responsible AI, content safety, and governance guardrails during build and deployment.
• Support post-go-live stabilization and production issue troubleshooting for deployed AI solutions.
• Guide junior engineers on Microsoft Foundry implementation patterns and best practices, without formal team-lead accountability.
• Contribute to reusable code assets, accelerators, and technical documentation for the AI Engineering job family.
• Stay current with the Microsoft Foundry roadmap and broader generative AI ecosystem, evaluating new capabilities for project use.
  
  

Qualifications

• 6–9 years in AI/ML or software engineering roles, with strong recent hands-on experience building solutions on Microsoft Foundry (or Azure AI Foundry/Azure AI Studio).
• Hands-on experience with Azure OpenAI Service, Microsoft Foundry model catalog, prompt engineering/prompt flow, and agent design.
• Practical experience building RAG solutions — vector databases/embeddings, Azure AI Search, and enterprise data grounding patterns.
• Working experience with agentic AI implementation — multi-agent orchestration, tool/function calling, and frameworks such as Semantic Kernel, AutoGen, or LangChain/LangGraph.
• Familiarity with the broader Azure data and AI ecosystem: Azure Machine Learning, Azure Cognitive Services, and data pipelines (Azure Data Factory/Synapse or Databricks) feeding AI solutions.
• Working knowledge of MLOps/LLMOps practices — model deployment, versioning, monitoring, and CI/CD for AI solutions.
• Awareness of Responsible AI principles and content safety/filtering practices.
• Strong programming skills in Python; familiarity with REST APIs and integration patterns for enterprise applications.
• Comfortable working directly with technical leads and client technical teams during delivery.
  
  

Preferred / Good To Have

• Microsoft certifications: Azure AI Engineer Associate (AI-102) or other Generative AI-related Microsoft credentials.
• Experience with Copilot Studio or Microsoft 365 Copilot extensibility.
• Exposure to CI/CD and DevOps practices for AI/data platforms (Azure DevOps, GitHub Actions).
• Experience working across multiple industry domains (manufacturing, BFSI, consumer goods, energy, healthcare, or others).
• Experience working in a global delivery / SI environment with distributed teams across geographies.