Join our innovative team as a Generative AI Engineer and play a crucial role in integrating advanced AI/ML and Generative AI technologies. This position focuses on creating intelligent, agentic applications powered by Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) pipelines. You will also be instrumental in developing intuitive and responsive frontend interfaces, bridging cutting-edge AI with exceptional user experiences.

This role is part of our Engineering as a Service/Operate division, emphasizing seamless integration and continuous improvement of AI capabilities within our products.

Design and implement sophisticated Generative AI solutions utilizing leading LLMs such as GPT, Claude, and LLaMA. Develop and meticulously optimize RAG pipelines, leveraging vector databases like ChromaDB for local development and Databricks Mosaic ML Vector Stores for production environments.

Build and maintain robust agentic workflows and conversational AI agents using frameworks like LangGraph and OpenAI. Perform essential vectorization using models such as GTE-large and BGE, with the option to fine-tune them for enhanced accuracy. Collaborate closely with backend and app development teams to seamlessly integrate Gen AI functionalities into our existing product suite.

A deep and practical understanding of LLMs, prompt engineering techniques, and transformer architectures is essential. Demonstrate hands-on experience with RAG architectures, efficient vector search, and various embedding models.

Proficiency in Python is a must, along with experience using libraries such as LangChain, Transformers, OpenAI SDK, or Hugging Face. Familiarity with agentic frameworks including AutoGen, OpenAI, CrewAI, or LangGraph is highly desirable. Prior experience deploying AI models effectively via APIs or microservices is also required.