As an AI/LLM Engineer, your primary focus will be building and optimizing Retrieval-Augmented Generation (RAG) models for large-scale medical and scientific search applications.
* Pre-process and embed over half a billion documents to ensure they are searchable and contextually accurate
* Improve the automated evaluation pipeline
* Fine-tune LLMs for textual RAG use cases
This is a heads-down, individual contributor role requiring strong communication and collaboration with the team. Essential skills include OpenSearch, Python development, API creation, model training, testing, and general backend programming.
Beyond these core competencies, experience in AWS infrastructure, RAG architectures, and LangChain for building LLM workflows using tools, memory, and retrieval is highly valued.
A background in Search Technology Experience – OpenSearch, building scalable search systems, and hands-on experimentation is necessary for this position.