Microsoft Foundry Lead

Role Summary 

Avanade India’s Artificial Intelligence practice is looking for a Microsoft Foundry Lead to drive the technical delivery of generative AI and agentic AI projects and programs built on Microsoft Foundry. This is a hands-on technical leadership role focused on execution — leading engineering teams through design, build, and deployment of AI solutions, ensuring engineering quality and delivery timelines, and acting as the go-to technical authority on live AI engagements within the practice. 

Key Responsibilities 

• Own technical delivery of Microsoft Foundry engagements — from solution design through build, testing, deployment, and go-live — across one or more concurrent projects. 
• Lead and mentor a team of AI engineers, guiding design decisions, code quality, and best practices on Microsoft Foundry-based builds. 
• Translate solution architecture into detailed technical design and implementation plans, working closely with Architects and Project/Program Managers. 
• Build and review 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. 
• Drive engineering standards — coding practices, CI/CD, testing, and performance optimization — across the delivery team. 
• Apply Responsible AI, content safety, and governance guardrails to solutions during build and deployment. 
• Troubleshoot and resolve complex technical issues during build and post-go-live stabilization; own production support escalations where needed. 
• Track and report delivery progress, risks, and technical dependencies to project/program leadership. 
• Support estimation and technical inputs for ongoing and upcoming project phases within the practice. 
• Contribute to reusable delivery accelerators, patterns, and best practices for the AI Engineering job family. 

.

• 8–12 years in AI/ML or software engineering roles, with strong recent hands-on experience delivering 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. 

• Experience with agentic AI implementation — multi-agent orchestration, tool/function calling, and frameworks such as Semantic Kernel, AutoGen, or LangChain/LangGraph. 

• Working knowledge of 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. 

• Understanding of MLOps/LLMOps practices — model deployment, versioning, monitoring, and CI/CD for AI solutions. 

• Awareness of Responsible AI principles, content safety/filtering, and AI governance in enterprise environments. 

• Strong programming skills in Python; familiarity with REST APIs and integration patterns for enterprise applications. 

• Proven experience leading a delivery team — technical mentoring, code/design reviews, and hands-on problem-solving under project timelines. 

• Comfortable working directly with project/program managers 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. 

.