Drive innovation as a Generative AI Engineer, connecting advanced AI technologies with exceptional user experiences. This role focuses on building intelligent, agentic applications powered by Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems. You will also be instrumental in crafting intuitive and responsive frontend interfaces.

This is an exciting opportunity to shape the future of AI integration within our organization.

Architect and deploy sophisticated Generative AI solutions leveraging LLMs like GPT, Claude, and LLaMA. Develop and refine RAG pipelines, utilizing vector databases such as ChromaDB for local development and Databricks Mosaic ML Vector Stores for production.

Construct and manage agentic workflows and conversational AI agents using frameworks including LangGraph and OpenAI. Implement vectorization techniques with models like GTE-large and BGE, with the option to fine-tune for enhanced precision. Collaborate closely with backend and application development teams to seamlessly integrate Gen AI capabilities into our products.

A strong foundation in LLMs, prompt engineering, and transformer architectures is essential. You should possess practical experience with RAG architectures, vector search, and embedding models. Proficiency in Python is required, along with familiarity in libraries such as LangChain, Transformers, OpenAI SDK, or Hugging Face.

Experience with agentic frameworks like AutoGen, OpenAI, CrewAI, or LangGraph is necessary. The ability to deploy AI models through APIs or microservices is also a key requirement.