Engineer

You are a talented and passionate RAG (Retrieval-Augmented Generation) Engineer with strong Python development skills, joining our AI/ML team in Bengaluru, India. Your role involves working on cutting-edge NLP solutions that integrate information retrieval techniques with large language models (LLMs). The ideal candidate will have experience with vector databases, LLM frameworks, and Python-based backend development. In this position, your responsibilities will include designing and implementing RAG pipelines that combine retrieval mechanisms with language models, developing efficient and scalable Python code for LLM-based applications, integrating with vector databases like Pinecone, FAISS, Weaviate, and more. You will fine-tune and evaluate the performance of LLMs using various prompt engineering and retrieval strategies, collaborating with ML engineers, data scientists, and product teams to deliver high-quality AI-powered features. Additionally, you will optimize system performance and ensure the reliability of RAG-based applications. To excel in this role, you must possess a strong proficiency in Python and experience in building backend services/APIs, along with a solid understanding of NLP concepts, information retrieval, and LLMs. Hands-on experience with at least one vector database, familiarity with Hugging Face Transformers, LangChain, LLM APIs, and experience in prompt engineering, document chunking, and embedding techniques are essential. Good knowledge of working with REST APIs, JSON, and data pipelines is required. Preferred qualifications for this position include a Bachelors or Masters degree in Computer Science, Data Science, or a related field, experience with cloud platforms like AWS, GCP, or Azure, exposure to tools like Docker, FastAPI, or Flask, and an understanding of data security and privacy in AI applications.,