Senior AI Technical Lead Agentic AI & Generative AI

Mandatory Skills:

(GenAI (3-5 Year) ,multi-agent architectures (5-8 Year), Architecture (5-8 Year) Agentic AI (3-5 Year) Python (8-10 years) Azure AI Foundry (8-10 years) Azure OpenAI (8-10 years) Azure AI Search (8-10 years) Azure AI Agent Service (8-10 years) AI Engineering Controls 8-10 years)

Role/Job Description

Role Senior AI Technical Lead Agentic AI & Generative AIExperience 15+ years overall; 5+ years Architecture; 3+ years hands-on GenAI / Agentic AIPrimary Focus Production-scale Agentic AI, Generative AI, multi-agent architectures and enterprise AI platformsCloud AWS / Azure / GCP experience with at least one cloud platform is mandatory1. Role Overview

We are seeking a Senior AI Technical Lead to own an Agentic AI engineering POD and lead the design, development and deployment of enterprise-grade Generative AI and multi-agent solutions. The role will translate functional requirements into technical workstreams, drive delivery across engineering PODs, contribute hands-on code, establish AI engineering standards, and mentor development teams.2. Key Responsibilities

Own the Agentic AI POD and deliver identified features in collaboration with Data, UI/UX, Infrastructure and otherPODs.Translate functional requirements into technical tasks, architecture decisions and executable delivery plans;drive the POD through implementation.Design and develop multi-agent solutions using Azure AI Foundry and Azure AI Agent Service.Build AI agents and implement agent orchestration, workflow management, memory and state-managementcomponents.Design and implement RAG solutions using Azure AI Search and vector stores.Develop prompt-engineering, tool-calling, function-calling and agent-collaboration frameworks.Implement observability, distributed tracing, evaluation and AgentOps capabilities.Develop Human-in-the-Loop workflows and agent recovery mechanisms.Contribute directly to code development, conduct code reviews and mentor development teams.Troubleshoot performance, response quality, hallucination, model/agent drift and orchestration issues.Define and implement AI governance, security and compliance controls.Lead development and deployment of production-grade Generative AI solutions.3. Mandatory Requirements Non-Negotiable

Candidates who do not meet ANY one of the following mandatory requirements should be rejected at screening

stage.

Experience: 15+ years overall professional experience AND 5+ years hands-on Architecture experience.GenAI / Agentic AI : 3+ years hands-on development experience in Generative AI and/or Agentic AI.Enterprise AI: Demonstrated development AND deployment of enterprise grade production GenAI solutions.Python: Strong hands-on expertise in Python.Azure AI Foundry: Hands-on project experience using Azure AI Foundry.Azure OpenAI: Hands-on project experience integrating/deploying LLM solutions using Azure OpenAI.Azure AI Search: Hands-on experience implementing RAG/search solutions using Azure AI Search.Azure AI Agent Service: Hands-on experience with Azure AI Agent Service.Multi-Agent Architecture: Production-scale multi-agent systems including orchestration, workflow, memory and state management.AI Engineering Controls: Hands-on governance, security, observability, evaluation and Human-in-the-Loop capabilities.Cloud: Hands-on exposure to AWS, Azure or GCP.Education: MS/M.Tech in CS, Information Systems, Computer Engineering or closely relevant discipline, or equivalent relevant degree.Evidence rule: mandatory skills must be demonstrable through actual employment/project experience. Skills

appearing only in a profile summary, keyword/skills section or certification list are not sufficient evidence. Failure on

any mandatory criterion = REJECT.

4. Required Skills

AI / GenAI: Generative AI, LLM applications, Agentic AI, multi-agent systems, RAG, prompt engineering, tool calling and function calling.Microsoft AI Stack: Azure AI Foundry, Azure OpenAI, Azure AI Search, Azure AI Agent Service, Document Intelligence and Azure AI services.AI Frameworks: Semantic Kernel, LangGraph, LangChain, AutoGen, MCP; practical agent orchestration and collaboration.Agent Engineering: Agent building, orchestration, workflow management, memory, state management, recovery and Human-in-the-Loop.AI Quality & Operations: Observability, tracing, evaluation, AgentOps, hallucination mitigation, performance/quality troubleshooting and drift management.Architecture: REST APIs, microservices, event-driven architecture, distributed systems and scalable enterprise architecture.Data & Storage: PostgreSQL, Cosmos DB, Redis, vector stores and enterprise retrieval architectures.Cloud & Deployment: Azure strongly preferred; AWS/GCP acceptable for the cloud requirement. Production AI deployment is essential.Engineering Practices: Code development, code reviews, technical documentation, Agile delivery and mentoring.Governance & Security: AI governance, security, compliance, responsible AI controls and enterprise .