Research Fellow

About the Role

The Singapore University of Technology and Design is seeking a Research Fellow for a two-year project on Vision-Language Models (VLMs) and efficient AI for drones. The project focuses on VLMs and multimodal learning for aerial imagery, efficient model design and compression, edge deployment, and intelligent drone applications such as scene understanding, navigation, and inspection.

Who We Are Looking For

• A PhD in Computer Science, Artificial Intelligence, Electrical Engineering, Robotics, or a closely related discipline.
• A strong research publication record, preferably with first-author papers at leading AI/ML/computer vision conferences such as NeurIPS, ICML, ICLR, CVPR, ICCV, ECCV, AAAI, or in journals such as IEEE TPAMI, IJCV, or IEEE TNNLS.
• Strong research experience in VLMs, multimodal foundation models, computer vision, or related deep learning methods.
• A good understanding of efficient model design, model compression, and optimisation for edge or embedded deployment.
• Proficiency in Python and PyTorch, with practical experience in model development, experimentation, and evaluation.
• The ability to conduct independent research, develop novel algorithms, and produce high-quality publications and systems.
• Experience with NVIDIA Jetson, TensorRT, ONNX, CUDA, ROS/ROS2, or UAV platforms is a strong advantage.