Join our innovative team as a Generative AI Engineer, where you'll be instrumental in merging advanced Generative AI technologies with exceptional user experiences. This role focuses on pioneering intelligent, agentic applications powered by Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) pipelines, while also ensuring the delivery of intuitive and responsive frontend interfaces.

Key responsibilities include designing and implementing robust Generative AI solutions leveraging LLMs like GPT, Claude, and LLaMA. You will develop and optimize RAG pipelines using vector databases such as ChromaDB for local development and Databricks Mosaic ML Vector Stores. Building and maintaining agentic workflows and conversational AI agents using frameworks like LangGraph and OpenAI is also central to this role. Additionally, you'll perform vectorization with models like GTE-large and BGE, with the option to fine-tune them for enhanced accuracy, and collaborate with backend and app teams to integrate Gen AI capabilities into our products.

We are looking for candidates with a profound understanding of LLMs, prompt engineering, and transformer architectures. Essential hands-on experience with RAG architectures, vector search, and embedding models is required. Proficiency in Python and key libraries such as LangChain, Transformers, OpenAI SDK, or Hugging Face is a must. Familiarity with agentic frameworks like AutoGen, OpenAI, CrewAI, or LangGraph, alongside experience deploying AI models via APIs or microservices, is crucial. A Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, or a related field, coupled with experience in cloud platforms (AWS, GCP, Azure) and CI/CD pipelines, is preferred.