We are looking for an AI RAG Engineer who can build and scale the data and retrieval layer powering AI agents and intelligent applications. The role will focus on designing databases, data pipelines, and RAG architectures that enable agents to securely access, retrieve, and use enterprise knowledge.nnnnnYou will work closely with AI/ML engineers, solution architects, and business teams to convert structured and unstructured enterprise data into reliable, searchable, and AI-ready knowledge.nnnnnWhat will you do nnDesign and build database architectures supporting AI agents and RAG-based applications.Build and maintain Retrieval-Augmented Generation (RAG) pipelines across multiple enterprise use cases.Develop data ingestion pipelines to bring data from databases, APIs, documents, knowledge repositories and other enterprise sources into AI-ready stores.Design and manage vector databases/vector search, embeddings, metadata and document chunking strategies.Implement hybrid retrieval approaches combining semantic, keyword, and structured database search.Develop data models and retrieval frameworks that allow multiple AI agents to securely access relevant knowledge.Optimize query performance, indexing, retrieval accuracy, and scalability.Build mechanisms for data freshness, versioning, access control, and source traceability.Work with AI/ML teams to evaluate and improve retrieval quality, relevance, and grounding of AI responses.Establish data governance, security, and permissioning for enterprise knowledge used by AI agents.Monitor database and RAG performance and troubleshoot data, retrieval,



and pipeline issues.Contribute to the design of reusable data and RAG components that can support multiple agents and use cases.nnnWhat will you need nnnnnMust-have skillsnn36 years of experience in database engineering, data engineering, or a closely related role.Strong experience with SQL and relational databases such as PostgreSQL, MySQL, or SQL Server.Hands-on experience with vector databases/vector search, such as Pinecone, Weaviate, Milvus, Qdrant or pgvector.Good understanding of RAG architecture and retrieval pipelines.Experience with embeddings, chunking, metadata management and semantic search.Solid Python skills and experience building data or API integrations.Experience working with REST APIs and data ingestion pipelines.Understanding of cloud data platforms such as AWS, Azure or GCP.Knowledge of database performance tuning, indexing and data modelling.Understanding of LLM-based applications and how data is consumed by AI agents.nnnGood to have skillsnnExperience with LangChain, LlamaIndex or similar AI application frameworks.Experience building multi-agent or agentic AI systems.Experience with document processing and unstructured data.Familiarity with knowledge graphs or Graph RAG.Experience with Redis or other caching technologies.Exposure to MLOps, LLMOps, or AI evaluation frameworks.Experience implementing enterprise security and role-based access controls for AI systems.nnnWhat Success Looks LikennMultiple AI agents can reliably access the right enterprise knowledge through a common, scalable data and retrieval layer.RAG pipelines deliver high-quality, relevant, and traceable context to LLMs.Data from different enterprise sources can be onboarded quickly into the AI ecosystem.Retrieval performance, data freshness, and security are consistently maintained.Reusable database and RAG components reduce the time required to launch new AI agents. .

📌 AI RAG Engineer (Gurugram)
🏢 WPP Production India [Studios]
📍 Gurugram