AI Engineer - RAG

Job Description

Job Summary: We are looking for a skilled and motivated AI Developer with hands-on experience in Retrieval-Augmented Generation (RAG) techniques. The ideal candidate should have a deep understanding of NLP, LLMs (like GPT, LLaMA, or similar), vector databases, and integration of retrieval mechanisms into generative models to create intelligent, context-aware systems. Key Responsibilities: Design and develop AI-powered applications using RAG-based architectures. Integrate large language models (LLMs) with retrieval systems such as vector databases (e.g., FAISS, Pinecone, Weaviate, Qdrant). Fine-tune and evaluate language models for domain-specific tasks. Implement document parsing, chunking, and embedding generation using NLP techniques. Create end-to-end pipelines for document ingestion, semantic search, and context-aware generation. Optimize performance and accuracy of RAG systems. Collaborate with cross-functional teams including data engineers, product managers, and frontend/backend developers. Key Requirements: Bachelor's/Master's degree in Computer Science, Artificial Intelligence, or a related field. 2+ years of experience in AI/ML development, with at least 1 year working on RAG or related LLM-based applications. Strong programming skills in Python and experience with libraries like LangChain, Hugging Face Transformers, PyTorch, etc. Hands-on experience with vector databases like FAISS, Pinecone, or Qdrant. Good understanding of semantic search, embeddings, and prompt engineering. Familiarity with APIs from OpenAI, Cohere, Hugging Face, etc. Knowledge of cloud services (AWS, Azure, GCP) is a plus. Strong problem-solving skills and a passion for innovation in generative AI. Job Type: Full-time Pay: Up to ₹1,000,000.00 per year Schedule: Day shift Application Question(s): How much experience do you have in building robust RAG-based systems? Are you comfortable relocating to Indore? Please mention your current ctc. Work Location: In person