Generative AI & LLM Engineer

About the Role

This position focuses on designing and building applications based on Generative AI and Large Language Models (LLMs). The role involves developing AI chatbots leveraging Retrieval-Augmented Generation (RAG) architecture, implementing advanced prompt engineering methods, and integrating LLMs with external APIs and databases to create seamless workflows.

Key Responsibilities

• Design and develop applications utilizing Generative AI and LLM technologies.
• Construct AI chatbots using RAG-based frameworks.
• Apply prompt engineering strategies to enhance AI response generation.
• Integrate language models with API endpoints and database systems.
• Create AI-driven workflows leveraging LangChain or LlamaIndex libraries.
• Utilize vector databases to enable efficient semantic search functionalities.
• Fine-tune LLMs to meet specific business objectives and optimize performance.
• Assess and evaluate the accuracy and efficiency of AI models.
• Deploy, maintain, and monitor AI applications within cloud infrastructure environments.

Skills and Experience Required

• Proficiency in Python programming for AI development.
• Practical experience working with Generative AI models and Large Language Models.
• Expertise in prompt engineering techniques and RAG architectures.
• Familiarity with LangChain or LlamaIndex AI frameworks.
• Hands-on knowledge of vector databases such as FAISS, Pinecone, or Chroma.
• Understanding of embedding techniques, semantic search, and natural language processing concepts.
• Experience integrating RESTful APIs and handling database connections.
• Knowledge of OpenAI APIs and usage of open-source LLMs.
• Comfortable working with cloud service platforms like AWS, Azure, or Google Cloud Platform.