RAG Engineers AI Developers - Remote

RAG Engineers + AI Developers Department: Artificial Intelligence & Data Engineering Experience Required: 3 to 6 Years Compensation (Market Standard): INR 2,400,000 to 3,800,000 Per Annum (CTC) Locations: Bangalore / Pune / Hybrid / Remote-flexible across India Role Overview & Key Parameters We are seeking a dedicated RAG Engineer + AI Developer to specialize in building advanced Retrieval-Augmented Generation systems that connect Large Language Models directly to complex enterprise knowledge bases. You will engineer sophisticated document parsing pipelines, semantic chunking strategies, embedding generation workflows, and hybrid search indexes to eliminate hallucinations and deliver precise, factual answers. Pipeline Architecture: Build end-to-end RAG pipelines encompassing document ingestion, OCR processing, semantic text splitting, and metadata tagging. Vector Search Optimization: Configure, tune, and manage vector databases and hybrid search engines (Pinecone, Qdrant, Weaviate, OpenSearch) for optimal recall and precision. Advanced Retrieval Techniques: Implement state-of-the-art retrieval enhancements, including query rewriting, multi-query expansion, hybrid keyword-vector search, and cross-encoder reranking. Evaluation & Benchmarking: Establish rigorous automated evaluation frameworks to measure retrieval hit rates, faithfulness, answer relevance, and context precision. Application Integration: Integrate optimized RAG retrieval components into customer-facing chat interfaces and enterprise search portals. Required Skills & Experience Specialized Experience: 3+ years focused on building production-grade RAG systems, semantic search engines, or NLP applications. Vector DB Mastery: Hands-on commercial experience with leading vector databases and modern embedding models. Python & Frameworks: Proficiency in Python alongside practical experience with LangChain, LlamaIndex, or custom retrieval frameworks. Analytical Rigor: Strong background in evaluating text retrieval quality, optimizing latency, and debugging complex unstructured data flows.