Interested applicants are invited to apply directly at the NUS Career Portal

Your application will be processed only if you apply via NUS Career Portal

We regret that only shortlisted candidates will be notified.

Job Description

Research Fellow - Multimodal Time-Series Analytics & Explainability development of algorithm and system for the project

The School of Computing at the National University of Singapore (NUS) invites applications for a Postdoctoral Research Fellow position in the area of time-series analytics and explainable AI. The successful candidate will contribute to the MOE-funded project "Time Will Tell (TwT)", which explores natural language-based interaction with time-series data. The role involves conducting research on multimodal learning and leading technical development efforts within the project.

Qualifications

Applicants should meet the following requirements:

• PhD Degree in Computer Science, Artificial Intelligence, Machine Learning, Data Science, or a related field, obtained within the last five year
• Research Experience in one or more of the following areas:Time-series analytics or forecasting
  Natural language processing (especially question answering or language grounding)
  Multimodal learning (e.g., combining text with temporal or numerical data)
  Explainable AI (XAI) or interpretable machine learning
• Strong Publication Record in reputable international conferences or journals (e.g., NeurIPS, ICML, ICLR, ACL, EMNLP, SIGMOD, VLDB)
• Technical Skills:Proficiency in Python and major deep learning frameworks such as PyTorch or TensorFlow
  Familiarity with transformer architectures and large language models (e.g., BERT, GPT)
  Experience in building, training, and evaluating deep learning models on real-world datasets
• Communication & Collaboration:Ability to work independently and as part of a collaborative research team
  Strong written and oral communication skills
  Commitment to mentoring graduate and undergraduate students
• Desirable (but not required):Experience with time-series QA datasets (e.g., Time-MQA, TSQA, MTBench)
  Background in signal processing or domain-specific time-series (e.g., financial, medical)
  Experience with open-source contributions or system/toolkit development