Experience: 4–6 Years

Location: Bangalore / Chennai

Job DescriptionWe are looking for an experienced AI/LLM Engineer with robust expertise in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and building production-ready Generative AI applications.

Key Responsibilities

- Design, develop, and deploy LLM-based applications using RAG architectures.
- Build document ingestion, preprocessing, chunking, embedding, and retrieval pipelines.
- Implement semantic search and vector database solutions for efficient information retrieval.
- Integrate LLMs with enterprise data sources, APIs, and applications.
- Optimize prompt engineering, retrieval accuracy, response quality, and application performance.
- Develop scalable AI solutions using Python and relevant ML/AI frameworks.
- Evaluate and improve LLM outputs, minimize hallucinations, and ensure reliable responses.
- Collaborate with cross-functional teams to deliver production-grade Generative AI solutions.

Required Skills




- 4–6 years of experience in AI/ML, NLP, or relevant software development.
- Strong hands-on experience with LLMs and RAG implementations.
- Proficiency in Python.
- Experience with LLM frameworks such as LangChain or LlamaIndex.
- Hands-on experience with embeddings, vector databases, and semantic search.
- Knowledge of prompt engineering and LLM integration through APIs.
- Experience building and deploying AI applications in production environments.
- Understanding of REST APIs, data processing, and application integration.

Preferred Skills
- Experience with cloud-based AI services such as AWS Bedrock, Azure OpenAI, or Google Vertex AI.
- Knowledge of RAG evaluation, reranking, hybrid search, and advanced retrieval techniques.
- Familiarity with Docker, CI/CD, and model/application monitoring.

📌 AI/LLM Engineer – RAG | 4-6 y | Bangalore, Chennai (Bengaluru)
🏢 Nasugroup.com
📍 Bengaluru