Generative AI Engineer

Experience

\n

3-8 Years

\n\n

Role Overview

\n

We are seeking a highly skilled MCP (Model Context Protocol), RAG (Retrieval-Augmented Generation), and Connectors Engineer to design, build, and optimize AI-powered solutions that integrate enterprise data sources with Large Language Models (LLMs). The ideal candidate will have hands-on experience with AI platforms, enterprise integrations, vector databases, retrieval pipelines, APIs, and modern AI application architectures.

\n

The role will focus on enabling secure, scalable, and context-aware AI experiences by developing MCP servers, building RAG pipelines, and integrating enterprise systems through custom connectors.

\n\n

Key Responsibilities

\n

MCP (Model Context Protocol)

\n

\n
• Design and develop MCP servers and tools for LLM-driven applications.
\n
• Implement tool-calling frameworks and agent integrations.
\n
• Enable secure exposure of enterprise capabilities to AI assistants.
\n
• Manage authentication, authorization, and governance of MCP services.
\n
• Optimize context-sharing mechanisms between AI models and enterprise systems.
\n

\n

RAG Engineering

\n

\n
• Design and implement enterprise-grade RAG architectures.
\n
• Build document ingestion, chunking, embedding, indexing, and retrieval pipelines.
\n
• Integrate vector databases and semantic search solutions.
\n
• Improve answer quality through reranking, hybrid search, and prompt optimization.
\n
• Monitor retrieval accuracy, latency, and hallucination rates.
\n
• Evaluate and implement advanced retrieval techniques.
\n

\n

Connectors & Integrations

\n

\n
• Develop connectors for enterprise systems such as:
\n
• SharePoint
\n
• Microsoft Graph
\n
• Azure Storage
\n
• Salesforce
\n
• ServiceNow
\n
• SAP
\n
• Databases (SQL/NoSQL)
\n
• Internal APIs
\n
• Build API integration frameworks and data synchronization pipelines.
\n
• Implement event-driven and real-time data access patterns.
\n
• Ensure scalability, security, and data compliance requirements.
\n

\n

AI Platform Development

\n

\n
• Collaborate with Data Scientists, AI Engineers, and Product Teams.
\n
• Build reusable AI integration frameworks and SDKs.
\n
• Develop observability, monitoring, and governance solutions.
\n
• Implement CI/CD pipelines for AI services.
\n
• Support production deployment and operational excellence.
\n

\n\n

Required Skills

\n

AI & LLM Technologies

\n

\n
• Strong understanding of Large Language Models (GPT, Claude, Gemini, Llama, etc.)
\n
• Hands-on experience with:
\n
• LangChain
\n
• LlamaIndex
\n
• Semantic Kernel
\n
• Azure AI Foundry / Azure OpenAI
\n
• AI Agents and Tool Calling
\n

\n

RAG Expertise

\n

\n
• Embeddings and vector search
\n
• Semantic search and hybrid retrieval
\n
• Metadata filtering
\n
• Document processing pipelines
\n
• Evaluation frameworks for RAG systems
\n

\n

MCP Knowledge

\n

\n
• Understanding of MCP architecture and ecosystem
\n
• MCP server development and tool registration
\n
• Context management and agent integration
\n

\n

Integration Development

\n

\n
• REST APIs
\n
• GraphQL APIs
\n
• OAuth 2.0 / OpenID Connect
\n
• Microsoft Graph API
\n
• Enterprise system integration patterns
\n

\n

Programming Skills

\n

\n
• Python (mandatory)
\n
• JavaScript / TypeScript
\n
• FastAPI, Flask, Node.js
\n
• SDK and API development
\n

\n

Data & Search Technologies

\n

\n
• Azure AI Search
\n
• Pinecone
\n
• Weaviate
\n
• Chroma
\n
• Elasticsearch / OpenSearch
\n
• SQL and NoSQL databases
\n

\n

Cloud Platforms

\n

\n
• Microsoft Azure (preferred)
\n
• AWS or Google Cloud (good to have)
\n
• Docker and Kubernetes
\n
• CI/CD pipelines
\n

\n\n

Preferred Qualifications

\n

\n
• Experience building Microsoft Copilot extensions and plugins.
\n
• Experience with Copilot Studio and Microsoft Graph Connectors.
\n
• Understanding of enterprise security and governance frameworks.
\n
• Exposure to Agentic AI and multi-agent architectures.
\n
• Knowledge of MLOps and AI observability tools.
\n
• Azure AI Engineer, Azure Developer, or related certifications.
\n

\n\n

Success Metrics

\n

\n
• Improved retrieval accuracy and response quality.
\n
• Reduced AI hallucinations through optimized RAG pipelines.
\n
• Successful integration of enterprise data sources.
\n
• High availability and performance of MCP services.
\n
• Adoption of AI solutions across business functions.
\n

\n\n

Nice-to-Have Experience

\n

\n
• Microsoft 365 Copilot extensibility
\n
• Graph Connectors
\n
• Azure AI Search
\n
• Copilot Studio
\n
• OpenTelemetry
\n
• Prompt Engineering
\n
• Multi-Agent Systems
\n
• Knowledge Graphs
\n
• Event-Driven Architectures
\n