Job no: 498912
Department: Infocomm Technology
Contract type: Contract
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 lead the research and development of a secure and privacy-preserving multimodal biometric authentication system for mobile devices using federated learning, supporting SIT’s mission as a university of applied learning through translational research that advances real-world applications in mobile security and user identity verification.

JOB REQUIREMENTS:

• Ph.D. degree in Computer Science, Electrical/Electronic Engineering, Information Systems, or a related field with a strong research focus in machine learning, biometrics, or mobile computing.
• Proven experience in federated learning, privacy-preserving machine learning, or distributed AI systems.
• Familiarity with biometric authentication systems, especially involving multimodal signals such as face, voice, and fingerprint recognition.
• Proficient in programming languages and frameworks commonly used in ML research, such as Python, PyTorch, TensorFlow, and mobile development environments (e.g., Android Studio or Swift/Xcode).
• Demonstrated ability to conduct independent research, as evidenced by peer-reviewed publications in relevant top-tier conferences or journals.
• Strong analytical and problem-solving skills, with the ability to design, implement, and evaluate complex algorithms in practical settings.
• Experience mentoring students and working collaboratively in multi-disciplinary research teams.
• Excellent written and verbal communication skills, with the ability to produce technical documentation and contribute to academic writing.

• Lead and conduct research on federated learning methodologies for multimodal biometric authentication on mobile devices, with emphasis on privacy-preserving techniques and real-world deployment.
• Develop and evaluate federated models that operate under positive-label-only constraints on local devices, focusing on scenarios where user templates are authentic and unimodal/multimodal verification must be robust against spoofing or deepfakes.
• Collaborate closely with the Principal Investigator (PI) to execute the project’s research plan, including literature review, algorithm design, experiment design, model training, evaluation, and benchmarking.
• Work with and supervise undergraduate or graduate student assistants, guiding them in data collection, software development, and research experiments.
• Contribute to the development of working prototypes and demonstrations for mobile biometric systems utilizing federated learning architectures.
• Prepare research documentation, including technical reports, conference/journal papers, and research grant progress updates.