Role Summary
As a key member of our team, you will be responsible for developing and optimizing Retrieval-Augmented Generation (RAG) models to search large-scale medical and scientific documents.
Key Responsibilities:
* Design and implement RAG models for efficient search across vast medical and scientific document repositories
* Pre-process and embed over half a billion documents to ensure they are searchable and contextually accurate
* Develop semantic chunking strategies, enhance the automated evaluation pipeline, and fine-tune Large Language Models (LLMs) for textual RAG applications
Requirements:
* At least 1 year of experience in Search Engineering or AI Engineering
* Proficiency in Search Technology – OpenSearch, building scalable search systems
* Strong background in Python development, including API creation, model training, testing, and backend programming
* Familiarity with LangChain for building LLM workflows using tools, memory, and retrieval