About me
I am currently an AI/ML Computational Scientist at Accenture Singapore, working under the AI Refinery Hub, where I focus on the deployment of cutting-edge AI solutions, particularly Large Language Models (LLMs), Vision-Language Models (VLMs), and multi-agent systems, across a wide range of industries including finance, retail, advertising, industrial automation, and supply chain.
Previously, I worked as a Research Scientist at the Advanced Remanufacturing and Technology Centre (ARTC), A*STAR, where I led projects on AI-driven manufacturing intelligence, including engineering drawing information extraction, CAD feature recognition, digital twin development, acoustic signal processing, and real-time process monitoring.
I hold a Ph.D. in Mechanical Engineering from Nanyang Technological University (NTU), where my research focused on AI-assisted in-situ process monitoring and multi-sensor fusion for advanced manufacturing systems. I also received my B.Eng. with Honours (Highest Distinction) from NTU in 2021.
While my earlier work centered around smart manufacturing, I have since transitioned into broader AI domains, applying scalable and production-grade ML solutions to real-world enterprise challenges.
Professional Experience
My core strengths lie in bridging foundational AI research and practical system deployment. I specialize in:
AI and Machine Learning
- Developing multi-modal machine learning systems combining vision, audio, and structured data
- Implementing and fine-tuning LLMs and VLMs (e.g., LoRA/QLoRA-based optimization) for Document Visual Question Answering
- Building agentic Retrieval Augmented Generation (RAG) pipelines and multi-agent frameworks
- Developing domain-specific knowledge graphs and integrating them into GraphRAG systems for RAG
- Designing prompt strategies and orchestration pipelines for task automation and reasoning
- Developing, and deploying various computer vision models, including classification, segementation (U-Net), object detection (YOLO)
- Audio signal processing and machine learning, Speech-to-Text model training and deployment, music classification and generation
Applied Intelligence Across Industries
- Automating knowledge retrieval and insight generation in domains such as:
- Finance – intelligent document understanding, compliance reasoning
- Retail & Advertisement – personalized recommendation, trend analysis
- Industrial AI – agent-based process automation, predictive maintenance
- Supply Chain – anomaly detection, demand forecasting
- Deploying AI models via APIs and containerized environments (FastAPI, Docker, MLflow)
Manufacturing Intelligence
- Developed digital twin frameworks for real-time manufacturing process monitoring
- Implemented CAD/CAM-based feature recognition and visual defect detection systems
- Built adaptive control systems using multi-modal sensor data and machine learning
- Conducted acoustic signal analysis for real-time welding quality monitoring and anomaly detection
- Developed ConvLSTM model for time-series defects forecasting in multi-layer 3D printing process.