Research Assistant, Department of Computer Science
On-siteHong Kong, Hong Kong
Hong Kong, Hong KongOn-siteContractBachelors DegreeEducation ServicesLarge
ContractBachelors DegreeLargeEducation Services
Job Summary
Undertake data engineering on large-scale Chinese medicine corpora, including in-depth data cleaning, structured format conversion, and de-duplication. Deploy and maintain the vector database while implementing the underlying retrieval-augmented generation (RAG) pipeline. Assist in factuality verification of model-generated content and perform statistical analysis of experimental evaluation data. Prepare research reports and academic papers under the guidance of core engineers. This project-based role focuses on applying large language model technology to Chinese medicine education, funded by the Chinese Medicine Development Fund.
Required Qualifications
- Bachelor's degree or above in Computer Science or a related discipline
- Proficiency in Python programming
- Database management
- Development
Desired Qualifications
- Experience with text processing
- Experience with OCR pipelines
- Experience with vector databases (e.g. FAISS, Milvus, Chroma)
- Experience with RAG or LLM application frameworks (e.g. LangChain, LlamaIndex)
- Detail-oriented
- Ability to work independently on large and heterogeneous text datasets
- Good command of written and spoken English and Chinese
- Experience in handling classical Chinese texts or Chinese medicine materials
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.