Job Description

Position: Gen AI & Copilot Developer

Exp : 3 to 8 Years

GenAI, Agentic AI & Copilot Developer :

with experience in building and deploying AI copilots, agentic AI solutions, and LLM-powered applications. The ideal candidate will have hands-on experience with OpenAI / Azure OpenAI, LLM orchestration frameworks (e.g., LangChain, Semantic Kernel), prompt engineering, and tool/function calling.


The role involves designing intelligent, multi-step agents that integrate with enterprise data and services to drive automation, reasoning, and decision-making. Experience with Microsoft Copilot extensibility and M365 integration is highly preferred.


1. Foundations of Generative AI


a. Understanding of LLMs (GPT, Claude, LLaMA, etc.)


b. Differences between generative AI vs traditional ML


c. Prompt engineering: Zero-shot, few-shot, chain-of-thought, and retrieval-augmented generation (RAG)


d. Model capabilities, limitations, and hallucination handling




2. Agentic AI Concepts


a. What is an AI Agent? How does it differ from a copilot?


b. Multi-step reasoning, task planning, and goal decomposition


c. Memory, context management, and tool usage


d. Knowledge grounding and external action execution


e. Use of frameworks like LangChain, Semantic Kernel, or CrewAI




3. Copilot Development (Microsoft Ecosystem)


a. Copilot extensibility in Microsoft 365 (e.g., Word, Excel, Outlook)


b. Copilot Studio: building custom copilots, integrating plugins


c. Graph connectors and Microsoft Graph API usage


d. Use of Power Platform (Power Automate, Power Apps) in AI-powered solutions




4. LLM Orchestration & Integration


a. LangChain/Semantic Kernel: chains, agents, memory, tools


b. Tool/function calling (e.g., OpenAI tool use, plugins)


c. Vector database integration (Pinecone, FAISS, Azure AI Search)


d. Data grounding (RAG pipelines)




5. Security, Privacy & Governance


e. Handling PII and enterprise data securely in GenAI solutions


f. Prompt injection, model output filtering, and misuse prevention


g. Monitoring and observability of AI agent behavior




6. Architecture and Deployment


a. Building scalable GenAI-powered APIs and microservices


b. Deploying to Azure, AWS, or hybrid environments


c. Using containerization and API gateways for modular agent-based services




7. Use Case Design and Real-World Scenarios


a. Walkthrough of past GenAI or agent projects (internal or POCs)


b. Business-centric use cases: HR assistant, policy copilot, knowledge bot, workflow automation


c. Measuring success: accuracy, user feedback, adoption




8. Soft Skills & Collaboration


a. Collaborating with business teams to translate requirements


b. Balancing innovation and feasibility


c. Communicating AI limitations clearly to stakeholders