RAG Engineers + AI Developers in India at Jobgether

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a RAG Engineers + AI Developers based in India.

We are looking for an experienced AI professional to build and optimize production-grade Retrieval-Augmented Generation (RAG) systems for complex enterprise knowledge environments. You will work across the full RAG lifecycle, from document ingestion and intelligent parsing to retrieval, reranking, evaluation, and application integration. The role offers the opportunity to work with Large Language Models, vector databases, semantic search, and modern AI frameworks. You will help improve the accuracy, relevance, speed, and reliability of AI-powered applications while reducing hallucinations. The environment is technically challenging and suited to engineers who enjoy solving complex problems involving unstructured data and information retrieval. You will collaborate across AI and data engineering initiatives to deliver scalable, customer-facing solutions.

• Design and develop end-to-end RAG pipelines covering document ingestion, OCR processing, semantic chunking, metadata extraction, embedding generation, retrieval, and response generation.
• Build and optimize vector and hybrid search solutions using technologies such as Pinecone, Qdrant, Weaviate, and OpenSearch.
• Implement advanced retrieval strategies, including query rewriting, multi-query expansion, hybrid keyword-vector search, and cross-encoder reranking.
• Develop robust document processing and knowledge ingestion workflows capable of handling complex and unstructured enterprise data.
• Integrate RAG and retrieval components into customer-facing conversational interfaces, enterprise search platforms, and other AI-powered applications.
• Establish automated evaluation and benchmarking frameworks to measure retrieval performance, context precision, answer relevance, faithfulness, and overall system quality.
• Continuously optimize retrieval accuracy, system latency, scalability, and reliability in production environments.
• Investigate and resolve issues across unstructured data pipelines, embeddings, retrieval systems, and LLM-powered applications.

• 3+ years of hands-on experience developing production-grade RAG systems, semantic search solutions, NLP applications, or closely related AI systems.
• Strong commercial experience working with vector databases and modern embedding models, with practical knowledge of vector and hybrid search architectures.
• Strong Python development skills and experience with frameworks such as LangChain, LlamaIndex, or comparable/custom retrieval frameworks.
• Solid understanding of Large Language Models, embeddings, semantic search, information retrieval, document processing, and RAG architecture.
• Experience implementing and evaluating advanced retrieval techniques such as query expansion, hybrid retrieval, reranking, and relevance optimization.
• Strong analytical and problem-solving skills, particularly in evaluating retrieval quality, improving latency, and debugging complex unstructured-data workflows.
• Bachelor's degree in Computer Science, Engineering, Artificial Intelligence, Data Science, or a related discipline.
• Ability to work independently in a technically demanding environment and collaborate effectively with AI, data, and engineering teams.
• Experience: approximately 3–7 years, with mid-to-senior-level expertise in relevant AI/RAG development.

• Annual compensation of approximately INR 2,400,000–3,800,000 CTC, depending on experience and skills.
• Full-time employment opportunity.
• Remote-friendly working model with flexibility across India.
• Opportunity to work on advanced AI, RAG, semantic search, and enterprise knowledge systems.
• Exposure to modern AI frameworks, vector databases, Large Language Models, and retrieval technologies.
• Location flexibility including Bangalore, Pune, hybrid, or remote across India.
• Opportunity to contribute to production-grade AI applications with direct impact on search quality, accuracy, and user experience.