Join our innovative team as a Generative AI Engineer, bridging cutting-edge AI with exceptional user experiences. You will be instrumental in crafting intelligent, agentic applications powered by Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) pipelines. Your work will ensure intuitive and responsive frontend interfaces are delivered seamlessly.

This role offers a unique opportunity to lead the development of next-generation AI solutions within an Engineering as a Service/Operate framework, focusing on integrating advanced AI capabilities into practical applications.

Design and implement advanced Generative AI solutions leveraging prominent LLMs like GPT, Claude, and LLaMA. Develop and refine RAG pipelines, incorporating vector databases such as ChromaDB for local setups and Databricks Mosaic ML Vector Stores for scalable solutions. Build and maintain sophisticated agentic workflows and conversational AI agents using frameworks like LangGraph and OpenAI.

Perform precise vectorization using models like GTE-large and BGE, with the option to fine-tune them for enhanced accuracy. Collaborate effectively with backend and application development teams to embed Gen AI functionalities into our product offerings.

A deep understanding of LLMs, prompt engineering techniques, and transformer architectures is essential. You should possess hands-on experience with RAG architectures, vector search mechanisms, and embedding models. Proficiency in Python, coupled with experience in libraries such as LangChain, Transformers, OpenAI SDK, or Hugging Face, is required.

Familiarity with agentic frameworks like AutoGen, OpenAI, CrewAI, or LangGraph is highly valued. Prior experience deploying AI models through APIs or microservices is also a key requirement for this position.