Generative AI Engineer – Agentic AI, RAG & MCP

Job Summary

We are looking for an experienced AI Engineer with solid expertise in Artificial Intelligence (AI), Generative AI, Agentic AI, Retrieval-Augmented Generation (RAG), and Model Context Protocol (MCP).

The ideal candidate should have proven experience delivering AI solutions in production environments, including developing and deploying AI agents, building scalable RAG pipelines, and integrating LLMs with enterprise systems and external tools. Knowledge of MCP or hands-on experience implementing MCP-based solutions is highly desirable.

Key Responsibilities

- Design, develop, and deploy AI-powered applications using Generative AI and Large Language Models (LLMs).

- Build and implement Agentic AI solutions capable of planning tasks, using tools, making decisions, and executing multi-step workflows.

- Develop and deploy production-ready RAG pipelines for enterprise knowledge retrieval and question-answering applications.

- Implement document ingestion, chunking, embedding generation, vector search, retrieval, reranking, and response generation.

- Integrate LLMs with enterprise applications, APIs, databases, and external tools.

- Implement MCP (Model Context Protocol) servers and clients to enable AI models and agents to securely access tools, resources, and enterprise data.

- Apply prompt engineering, context management, structured outputs, and model evaluation techniques.

- Deploy, monitor, troubleshoot, and optimize AI applications in production environments.

- Improve AI solution performance, scalability, reliability,



latency, and cost efficiency.

- Implement appropriate security, access controls, data privacy, and guardrails for AI applications.

- Collaborate with data engineers, software developers, architects, and business stakeholders to deliver AI solutions.

Mandatory Skills

- Strong experience in AI/ML and Generative AI application development.

- Hands-on experience building and delivering Agentic AI solutions in production.

- Proven experience developing, deploying, and maintaining production-grade RAG applications.

- Strong understanding of LLMs, prompt engineering, embeddings, vector databases, and semantic search.

- Knowledge of MCP (Model Context Protocol), with hands-on implementation or integration experience preferred.

- Experience integrating AI models with APIs, tools, databases, and enterprise applications.

- Experience deploying AI applications and supporting them in production.

Technical Skills

- Programming: Python; experience with REST APIs and backend development.

- LLMs: OpenAI models, Azure OpenAI, Anthropic Claude, or equivalent LLM platforms.

- Agentic AI: LangGraph, LangChain agents, LlamaIndex workflows, or similar frameworks.

- RAG: Vector databases such as Pinecone, FAISS, Weaviate, Chroma, or Azure AI Search.

- Embeddings and Retrieval: Semantic search, hybrid search, reranking, and context optimization.

- MCP: MCP servers, clients, tools, resources, and integration with AI agents.

- Deployment: Docker, cloud platforms such as AWS, Azure, or GCP; CI/CD and application monitoring.

📌 Generative AI Engineer – Agentic AI, RAG & MCP (Hyderabad)
🏢 Infosys APAC
📍 Hyderabad