Backend Engineer: RAG Model Developer
We are seeking a skilled Backend Engineer to join our team in developing Retrieval-Augmented Generation (RAG) models for search across large-scale medical and scientific documents.
Your primary focus will be on building and optimizing RAG models, pre-processing and embedding over half a billion documents to ensure they are searchable and contextually accurate.
You'll work on semantic chunking strategies, improving the automated evaluation pipeline, and fine-tuning LLMs for textual RAG use cases.
This is a hands-on experimentation role, requiring expertise in model development, backend engineering, and collaboration with DevOps for production rollout.
A strong background in software development, particularly in Python, is essential. Experience with OpenSearch, AWS infrastructure, and LangChain is highly desirable.
Key Responsibilities:
* Design, develop, and deploy RAG models for search applications.
* Develop and maintain high-quality software components using Python.
* Collaborate with cross-functional teams to integrate RAG models with existing systems.
* Optimize RAG models for performance, scalability, and reliability.
Requirements:
* 1+ years of experience as a Search Engineer or AI Engineer.
* Strong understanding of software development principles and practices.
* Experience with OpenSearch, AWS infrastructure, and LangChain is highly desirable.
Nice to Have Skills:
* Familiarity with containerization using Docker.
* Knowledge of cloud-based services such as AWS S3 and IAM.