Engineer

As a talented and passionate RAG (Retrieval-Augmented Generation) Engineer with strong Python development skills, you will be joining the AI/ML team in Bengaluru, India. Your role will involve working on cutting-edge NLP solutions that integrate information retrieval techniques with large language models (LLMs). The ideal candidate for this position will have experience with vector databases, LLM frameworks, and Python-based backend development. **Key Responsibilities:** - Design and implement RAG pipelines that combine retrieval mechanisms with language models - Develop efficient and scalable Python code for LLM-based applications - Integrate with vector databases like Pinecone, FAISS, Weaviate, and more - Fine-tune and evaluate the performance of LLMs using various prompt engineering and retrieval strategies - Collaborate with ML engineers, data scientists, and product teams to deliver high-quality AI-powered features - Optimize system performance and ensure the reliability of RAG-based applications **Qualifications Required:** - Strong proficiency in Python and experience in building backend services/APIs - 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 - Experience in prompt engineering, document chunking, and embedding techniques - Good knowledge of working with REST APIs, JSON, and data pipelines In addition to the above, 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.,