RAG AI Developer (LLM + Retrieval)

This role is for one of the Weekday's clients Min Experience: 1 years Location: Mumbai JobType: full-time We are seeking a RAG AI Developer to design, build, and optimize retrieval-augmented generation solutions for EdTech-focused AI products such as course Q&A systems, tutor assistants, content discovery tools, and internal knowledge platforms.
This is a hands-on role focused on building end-to-end RAG pipelines, improving answer accuracy, reducing hallucinations, and deploying scalable AI services that deliver fast, reliable, and well-cited responses.
Key Responsibilities Build and maintain end-to-end  RAG pipelines , including document ingestion, chunking, embeddings, retrieval, and generation Implement and optimize  hybrid search strategies  combining semantic and keyword-based retrieval Integrate LLMs using frameworks such as  LangChain, LlamaIndex , or custom-built pipelines Work with  vector databases  to optimize indexing, retrieval speed, and relevance Design reranking strategies, metadata filtering, and retrieval tuning for improved answer quality Develop evaluation frameworks and metrics to measure relevance, faithfulness, and context accuracy Reduce hallucinations through prompt design, guardrails, and citation-based response generation Build and deploy APIs and services using  FastAPI or Flask , with monitoring for latency and cost Implement caching and optimization strategies to improve performance and efficiency Collaborate with product and content teams to define data sources, workflows, and use cases What Makes You a Great Fit 1+ year of hands-on experience building  NLP or LLM-based features , with exposure to RAG or retrieval systems Strong proficiency in  Python  and experience working with text-processing pipelines Practical knowledge of embeddings, chunking strategies, and document loaders (PDF, HTML, DOC formats) Experience with at least one  vector database  and common similarity or retrieval methods Solid understanding of core machine learning and NLP concepts Familiarity with modern LLMs (open-source or hosted) and prompt engineering techniques Experience deploying AI services and APIs, with an understanding of performance and cost trade-offs Ability to collaborate effectively with cross-functional teams in a product-driven environment Interest in building scalable, accurate, and user-focused AI systems, especially within EdTech use cases