"Research Engineer"

As a University of Applied Learning, SIT works closely with industry in our research pursuits. Our research staff will have the opportunity to be equipped with applied research skill sets that are relevant to industry demands while working on research projects in SIT.

The Research Engineer will play a key role in automated wildlife identification and classification from trap camera images using cutting-edge computer vision technology. Working closely with the Principal Investigator, Co-PI, and interdisciplinary research team, RE will develop and implement deep learning algorithms to analyze trap camera footage for wildlife monitoring and conservation efforts.

Job Responsibilities

• Participate in and manage the research project together with the PI, Co-PI, and research team to ensure timely achievement of project deliverables.
• Undertake the following specific responsibilities in the project:
• Develop, train, and optimise deep learning models for wildlife species identification, classification, and segmentation using real-world datasets.
• Design and implement software modules to integrate the models into a working system prototype.
• Perform data annotation.
• Conduct experiments, analyse results, and iterate models for improved accuracy and efficiency.
• Prepare project documentation, technical reports, and academic publications.
• Collaborate with industry partners and contribute to technology transfer efforts.
• Support the design of simple web interfaces or dashboards to visualise CV model outputs, working alongside developers when needed.
• Contribute to system integration by applying familiarity with backend/frontend workflows, ensuring CV models can be accessed through user-facing applications.
• Assist in deployment of CV solutions on cloud or edge platforms with basic interface support for end-users.

The candidate is to liaise and communicate with any internal or external stakeholders to ensure project deliverables are met and to perform any other adhoc duties assigned by Supervisor.

Technical Requirements:

• Possess strong technical knowledge and hands-on experience in:
• Deep learning frameworks (e.g., PyTorch, TensorFlow, Keras)
• Computer vision models for object detection and classification (e.g., YOLO, R-CNN variants, EfficientNet, ResNet, U-Net)
• Image processing and computer vision techniques
• Python programming and relevant libraries (e.g., OpenCV, NumPy, scikit-learn, Pandas, Matplotlib)
• Experience with dataset preparation, model training, and performance evaluation
• Candidates with strong computer vision expertise and proven success in 1-2 substantial CV projects are welcome to apply regardless of domain-specific experience

Familiarity with Web/Full-Stack Development:

• Basic understanding of frontend frameworks (e.g., React, Angular, or Vue.js)
• Exposure to backend development (e.g., Flask, Django, Node.js)
• Awareness of RESTful APIs and microservices architecture.
• General knowledge of database systems (SQL/NoSQL).
• Experience with cloud platforms (AWS, GCP, Azure) for deployment and scaling

Educational Requirements:

• Hold at least a Bachelor's degree in Computer Science, Software Engineering, Data Science, or a related technical field
• Master's or PhD degree in Machine Learning, Computer Vision, or related areas will be advantageous

Preferred Qualifications:

• Experience with biological/ecological datasets or wildlife imagery
• Familiarity with data annotation tools and practices for large-scale datasets
• Knowledge of model deployment and optimization (e.g., ONNX, TensorRT, model quantization)
• Experience with edge computing or embedded systems (e.g., NVIDIA Jetson, Raspberry Pi)
• Background in real-time processing and GPU acceleration (CUDA)
• Participation in relevant competitions (e.g., Kaggle, computer vision challenges)
• Experience with version control (Git) and collaborative development practices