Research Institute for Federated Learning
Research Assistant
(Ref. 260811001)
[Appointment period: twelve months]
Duties
The appointee will assist the project leader in the research project - “Multimodal intent recognition and common-issue analysis for customer satisfaction”. He/she will be required to:
(a) process and analyse multimodal customer touchpoint data, including voice-of-customer feedback, application usage records and structured data;
(b) develop customer intent recognition models for noisy, colloquial and regionally diverse user data;
(c) design and implement methods for the automated construction and application of intent knowledge graphs;
(d) develop models for common-issue discovery, evaluation, prioritization and root-cause attribution by integrating user intent, user journey information, structured features and knowledge graphs;
(e) conduct model implementation, experimental evaluation, code maintenance, technical documentation and research report preparation;
(f) provide research support for related projects involving multimodal learning, foundation models and domain-specific artificial intelligence applications;
(g) support the translation of academic research into industrial applications and the preparation of patents and research papers; and
(h) perform any other duties as assigned by the project leader, Director of Unit or their delegates.
Qualifications
Applicants should:
(a) have a good honours degree or above in Computer Science, Artificial Intelligence, Data Science, Electronic Engineering or a related discipline; a master’s degree would be an advantage;
(b) have a solid background in one or more of the following areas: natural language processing, multimodal learning, large language models, knowledge graphs, graph learning or data mining;
(c) be proficient in Python and deep learning frameworks such as PyTorch, with strong AI-assisted coding capabilities and practical experience in using AI coding tools to support code generation, debugging, refactoring, testing and documentation;
(d) have experience in data preprocessing, model development, experimental evaluation and technical documentation;
(e) have experience in Chinese natural language processing, user behavior analysis, knowledge graph construction, computer vision, image segmentation or foundation-model adaptation, which would be an advantage;
(f) have a good command of both English and Chinese; and
(g) be self-motivated, responsible and be able to work independently as well as collaboratively in a research team.
Preference will be given to those who have relevant research experience, publication or software development experience.
Applicants are invited to contact Prof. Di Jiang at telephone number 2766 7281 or via email at di-prof.jiang@polyu.edu.hk for further information.
Conditions of Service
A highly competitive remuneration package will be offered.
Consideration of applications will commence on 18 August 2026 until the position is filled.
Posting date: 11 August 2026