Research Fellow/ Research Engineer (Automated Loading & Unloading System of ULDs) - LX(1134)

Job Purpose 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 primary responsibility of this role is to conduct applied research on the aircraft cargo Automated Loading and Unloading System of Unit Load Devices (ULDs) project. The role will develop and validate an AI-enabled multimodal perception pipeline for ULD alignment and positioning, Cargo Loading System (CLS) lock-state verification, and final operational safety checks within a representative Lower Deck Cargo Compartment (LDCC) environment. Key Responsibilities • Participate in and manage research activities with the Principal Investigator (PI), Co-PI and project team to ensure that milestones, technical performance measures and deliverables are met. • Analyze operational requirements and define representative perception scenarios, safety-check criteria, lighting conditions and occlusion cases for ULD positioning and CLS lock verification. • Collect, synchronize, annotate and curate RGB and depth-sensor datasets, including ground-truth labels for ULD alignment and lock. • Develop representative digital simulation assets and synthetic-data workflows for LDCC, ULD and CLS-lock geometries, reusing relevant assets from other work packages where appropriate. • Design, train and evaluate computer-vision and multimodal perception models for ULD alignment verification, CLS lock-state detection, and final safety assessment. • Integrate depth sensing and sensor fusion to improve robustness in confined spaces with reflective surfaces, repetitive structures, variable lighting and partial occlusion. • Implement confidence estimation and support remote checking or human intervention for low-confidence cases. • Deploy and validate the perception pipeline in laboratory and representative LDCC mock-up environments; benchmark performance against manually labelled ground truth. • Integrate outputs with robotic manipulation, navigation and system-integration work packages, and support end-to-end demonstrations with collaborators and industry stakeholders. • Document datasets, models, evaluation procedures and results; contribute to technical reports, invention disclosures, publications and presentations. • Carry out risk assessments and ensure compliance with Workplace Safety and Health requirements, data governance, research integrity and project IP/confidentiality obligations. Job Requirement • Bachelor’s degree in Computer Science, Computer Engineering, Electrical/Electronic Engineering, Robotics, Artificial Intelligence, or a closely related discipline, with at least three years of relevant work experience; or a postgraduate degree (Master’s or PhD) in one of these fields. • Strong research competence in deep learning and computer vision, with hands-on experience in object detection, segmentation, pose or alignment estimation, depth perception, 3D vision or multimodal sensor fusion. • Proficiency in Python and a modern deep-learning framework such as PyTorch or TensorFlow, with practical experience developing and evaluating perception pipelines. • Experience with RGB-D cameras, depth sensors, robotics middleware such as ROS/ROS 2, or simulation platforms such as NVIDIA Isaac Sim will be advantageous. • Experience with dataset collection, annotation, synthetic-data generation, experiment design and quantitative model validation under real-world variations. • Strong research record evidenced by peer-reviewed publications, technical reports, patents, open-source software or comparable applied R&D outputs. • Ability to work with physical robotic systems and within a representative cargo-compartment mock-up; prior experience in safety-critical, aviation, logistics or industrial automation applications is advantageous. Key Competencies • Strong analytical and critical-thinking skills, with the ability to translate operational requirements into measurable perception and safety-verification criteria. • Proficient in experimental design, reproducible AI development, performance benchmarking, troubleshooting and technical documentation. • Able to write research papers and technical reports and communicate results clearly to academic, engineering and industry audiences. • Able to build effective working relationships with researchers, engineers, vendors, airport stakeholders and industry collaborators within and outside the university. • Able to work independently and collaboratively across perception, robotics, navigation and system-integration teams. • Self-directed learner who shows initiative, takes ownership of work and adapts to evolving project requirements.