Batu Pahat, Johore, Malaysia
Dr. Tan brings over a decade of research and development experience spanning both academia and industry, including collaborations with private enterprises and startups. His areas of expertise encompass image processing, computer vision, and machine learning, with practical applications in biometrics, image classification, object detection, and segmentation. He began his career in academia at higher education institutions, where he built a strong research foundation, before transitioning into the industry. In his current role as a Senior Staff Engineer (Data Science) at Infineon Technologies, Dr. Tan leverages his multidisciplinary background to address complex, real‑world challenges. At Infineon, he serves as the Wide-Bandgap (WBG) Digitalization Ambassador, leading strategic initiatives such as quick/short test analytics solutions, wafer defect root-cause analysis, and automation enablement. He also drives the development of RESTful API-based reporting services and advanced annotation modules that enhance the wafer pattern catalog—supporting accurate defect pattern recognition and wafer health factor assessment. In addition to his technical leadership, Dr. Tan actively contributes to capability building by conducting training aligned with the organization’s digitalization roadmap. He is also committed to talent development, providing mentorship and guidance to junior colleagues while supporting both technical innovation and research publication efforts.
• Wide-bandgap (WBG) digitalization ambassador. • WBG quick/short test analytic solution. • Wafer defect root cause analysis. • Automation enablement. • Development of RESTful API for report generation service. • Development of annotation modules designed to enhance the wafer pattern catalog, a comprehensive knowledge base utilized for matching and identifying defect patterns on wafers (wafer health factor). • Conduct training to support for digitalization roadmap.
• Led development of AI projects focusing on several areas: o Image/video processing/computer vision: image classification, object detection & segmentation, image generation, super-resolution, background removal, face detection, age and gender estimation, etc. o Audio: audio denoising, wav2lip, speech-to-text enhancement. o NLP/LLM: topic classification, tag/keyword suggestions, descriptive template (JSON/YAML) generation to be used for video creation. • Implemented document processing solution using Dotnet to extract objects (text, image, video, audio) and corresponding metadata (e.g., coordinates, formatting etc) from PDF/PowerPoint, which such information are to be fed to the company’s video creation solution. • Provided recommendations in defining product roadmap, as well as provided proof-of-concepts and rapid prototyping that leveraging on container technology (e.g. Docker) to drive better decision making. • Developed data processing pipeline (ETL) using AWS Glue to process raw data to facilitate client usage analysis, as part of the continuous improvement and optimization of the product features which eventually drive better client satisfaction level and improved churn rate to ensure the sustainability of the business. • Conducted extensive research on emerging AL/ML technologies to drive development of innovative solutions. • Advocated and implemented the use of MLOps (mlflow) for AI/ML experiments to encourage better collaboration, monitoring and reproducibility. • Evaluated external API services as well as to liaise with the service providers for API integration.
• Conducted experiments for stock prices by leveraging on various SOTA predictive modelling, i.e., ARIMA, SARIMA, boosting algorithms, and LSTM. • Conducted research and development for medical image analysis, i.e., fundus image analysis by leveraging on deep learning algorithms. • Implemented model serving and versioning pipeline by leveraging on TF Serving and containerization (Docker). • Produced research publications and patent filing.
• Spearheaded research and development of the AI healthcare solutions. Architected the AI solutions by defining the guidelines and procedures for various DL operations, e.g., data acquisition, data annotation & review, data processing & augmentation, model training & evaluation, model deployment, and continuous model improvement using transfer learning/fine-tuning strategies. • Implemented in-house video annotation tool to improve the annotation efficiency by more than 80%. • Defined and developed DL pipeline to enable in-house model training and refinement in an isolated environment in order to comply with PDPA requirements to dealing with sensitive data. Automated on-site DL training and refinement process using Jenkins. • Setup and managed cloud (AWS) instances for data processing and model training.