Job Title: AI Engineer (Search Engine)
* Develop semantic chunking strategies to enhance the automated evaluation pipeline for a Retrieval-Augmented Generation (RAG) service.
Key Responsibilities:
Build and optimize RAG models for search across large-scale medical and scientific documents, including pre-processing and embedding over half a billion documents to ensure they are searchable and contextually accurate.
* Experiment with different model architectures and fine-tune Large Language Models (LLMs) for textual RAG use cases.
Collaboration and Communication:
Work closely with DevOps for production rollout and ensure seamless integration with backend features. Strong communication and collaboration with the team is essential.