Join our dynamic team as an innovative Generative AI Engineer, focusing on creating intelligent applications. This role is crucial for bridging advanced Generative AI technologies with exceptional user experiences. You will be instrumental in developing agentic applications powered by Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) pipelines, ensuring seamless and intuitive frontend interfaces.

Key duties include designing and implementing sophisticated Generative AI solutions using LLMs like GPT, Claude, and LLaMA. You will develop and fine-tune RAG pipelines with vector databases (ChromaDB for local, Databricks Mosaic ML for cloud) and build robust agentic workflows and conversational AI agents using frameworks such as LangGraph and OpenAI. Additionally, you will perform vectorization, optimize embedding models (GTE-large, BGE), and collaborate closely with backend and app development teams to integrate Gen AI capabilities into our products.

Ideal candidates possess a deep understanding of LLMs, prompt engineering, and transformer architectures. Proven hands-on experience with RAG, vector search, and embedding models is essential. Proficiency in Python, coupled with experience in libraries like LangChain, Transformers, OpenAI SDK, or Hugging Face, is required. Familiarity with agentic frameworks such as AutoGen, OpenAI, CrewAI, or LangGraph, and experience deploying AI models via APIs or microservices are also necessary.