Backend Engineer for RAG Model Development
We are seeking an experienced Backend Engineer to join our team in developing and optimizing Retrieval-Augmented Generation (RAG) models. As a key member of this project, you will focus on building scalable features that enhance the search capabilities across large-scale medical and scientific documents.
Responsibilities:
* Semantic chunking strategies to ensure accurate context and facilitate efficient information retrieval.
* Improvement of automated evaluation pipelines to measure model performance effectively.
* Fine-tuning Large Language Models (LLMs) for textual use cases, including sentiment analysis and text classification.
Requirements:
* Proven experience in backend development using languages such as Java or Python.
* Strong understanding of algorithms and data structures to optimize RAG model performance.
* Experience with cloud-based services and containerization platforms like Docker.
Benefits:
This is an excellent opportunity for individual contributors who thrive in heads-down environments while still maintaining strong communication and collaboration skills within the team.