About This Role
Seeking an AI Engineer to design, build, and optimize production-grade Retrieval-Augmented Generation (RAG) systems using LangChain and modern LLM infrastructure, focusing on embeddings, vector databases, chunking strategies, and cost-performance tradeoffs.
Key Responsibilities
- Design and implement scalable RAG pipelines
- Optimize embedding and chunking strategies
- Build multi-retriever and hybrid search systems
- Develop document ingestion pipelines
- Implement LangChain agents, tools, and memory systems
- Integrate vector databases with metadata filtering
- Optimize token usage, latency, and cost
- Build evaluation pipelines and hallucination mitigation systems
Requirements
pythonlangchainproduction RAG implementationvector databasesfastapirest apidockerdistributed systems knowledge
Nice to Have
langgraphllamaindexkafkarediskubernetesfine-tuningmodel quantizationgraph RAGself-hosted LLM inference optimization
Additional Information
- understand embeddings, vector databases, chunking strategies, context optimization, hallucination control, cost-performance tradeoffs
Frequently Asked Questions
What is the salary for this AI Engineer Langchain & RAG position?
The salary range for this AI Engineer Langchain & RAG position is ₹20.0L/year per year.
What experience is required for this role?
This AI Engineer Langchain & RAG position requires 4-6 years of experience.
Where is this job located?
This AI Engineer Langchain & RAG position is based in Remote.
What skills are required?
Required skills include: python, docker, kubernetes.