Generative AI / LLM Engineer

## About the Role We are looking for a Generative AI / LLM Engineer who has hands-on experience building AI-powered products, conversational agents, and intelligent assistants using Large Language Models. The ideal candidate should have experience designing AI agent architectures, memory systems, retrieval-based pipelines, and prompt orchestration frameworks. This role requires someone who has built real-world AI applications such as chatbots, intelligent assistants, AI dashboards, or automation systems using LLMs and vector databases. ## Key Responsibilities - Design and develop AI-powered chatbots and conversational agents using LLMs. - Build memory architectures for AI systems to retain user context, preferences, and conversation history. - Develop Retrieval Augmented Generation (RAG) pipelines using vector databases and embedding models. - Implement AI agent frameworks to orchestrate prompt chains, memory layers, and decision-making workflows. - Design intelligent systems that can analyze user inputs, reference past interactions, and automate multi-step tasks. - Build evaluation frameworks for AI models to measure performance, accuracy, and response quality. - Develop AI assistants for content generation, automation, or data analysis. - Work with prompt engineering and model optimization to improve response quality. - Develop backend services and APIs for AI applications using Python-based frameworks. - Build AI-driven dashboards and tools that allow natural language querying and automated reporting. - Work closely with product and engineering teams to build scalable AI-powered products. ## Required Skills - Strong programming experience in Python - Hands-on experience with Large Language Models (LLMs) - Experience building AI Chatbots / Conversational AI - Strong experience with RAG (Retrieval Augmented Generation) - Experience with Vector Databases and Embeddings - Experience designing AI Agent architectures - Strong knowledge of Prompt Engineering - Experience building AI APIs or backend services - Familiarity with Cloud platforms (GCP preferred) ## Good to Have - Experience with Computer Vision / OCR - Experience with Diffusion Models or GANs - Experience building LLM-based dashboards or reporting tools - Experience working with AI agent frameworks or orchestration tools ## Ideal Candidate Profile - Experience working on Generative AI products or prototypes - Hands-on experience with LLM-based assistants or chatbots - Strong understanding of AI system design, memory layers, and retrieval pipelines - Ability to convert AI research concepts into production-ready applications