<- All Jobs
RAG Content Retrieval Backend Engineer - ByteRec
About The Team
The Volcano Engine Vector Database Knowledge Base team supports both internal and ToB customer requirements. We are responsible for the content processing of the Volcano Engine large model Knowledge Base and the design and development of the retrieval system architecture, including framework construction, new feature delivery, and system stability assurance.
Responsibilities
1. Participate in the backend development and delivery of the framework and middleware of the large model RAG architecture, and implement the feature delivery and demand support of the Public Cloud products;
2. Based on the application scenarios of large models, provide a general-purpose domain Knowledge Base solution, encapsulate common patterns and processes, and provide stable external service capabilities;
3. Participate in the maintenance and expansion of the backend architecture of the self-developed vector database, and provide the processing and storage capabilities of MultiModal Machine Learning unstructured data on the vector database product;
4. Participate in the iterative development of capabilities such as backend debugging, monitoring, billing, and elastic scheduling for the Public Cloud products of the vector database and Knowledge Base.
The Volcano Engine Vector Database Knowledge Base team supports both internal and ToB customer requirements. We are responsible for the content processing of the Volcano Engine large model Knowledge Base and the design and development of the retrieval system architecture, including framework construction, new feature delivery, and system stability assurance.
Responsibilities
1. Participate in the backend development and delivery of the framework and middleware of the large model RAG architecture, and implement the feature delivery and demand support of the Public Cloud products;
2. Based on the application scenarios of large models, provide a general-purpose domain Knowledge Base solution, encapsulate common patterns and processes, and provide stable external service capabilities;
3. Participate in the maintenance and expansion of the backend architecture of the self-developed vector database, and provide the processing and storage capabilities of MultiModal Machine Learning unstructured data on the vector database product;
4. Participate in the iterative development of capabilities such as backend debugging, monitoring, billing, and elastic scheduling for the Public Cloud products of the vector database and Knowledge Base.