Career

I joined the LumineAI project team at President Information CORP. as a Generative AI Engineer. My work focuses on building enterprise-grade AI solutions by integrating advanced LLM architectures with robust cloud infrastructure to ensure high scalability and operational efficiency.

• Engineered AI-driven conversational systems using OpenAI’s LLM APIs and RAG (Retrieval-Augmented Generation) to deliver high-accuracy, context-aware responses for the LumineAI project.
• Developed custom plugins to extend chatbot functionalities, significantly enhancing system usability and tailoring features to meet specific business needs.
• Collaborated on infrastructure design using Google Kubernetes Engine (GKE), ensuring the stability, high availability, and seamless scalability of AI services.
• Optimized CI/CD pipelines via GitHub Actions, automating the end-to-end workflow from code integration to deployment on Kubernetes clusters, reducing manual overhead.

I joined the Systems Division of Tunghai University’s Library and Information Services Office in Aug. 2023. I continued to hone my skills by working on projects that leveraged Generative AI to build chatbots by utilized OpenAI’s large language model (LLM) API and RAG (Retrieval-Augmented Generation) to provide accurate and user-friendly responses.

• By leveraging RAG (Retrieval-Augmented Generation) with OpenAI LLM API, I developed an AI chatbot that is not just a technical feat, but also a practical solution based on school-wide domain knowledge.
• Fine-tuned a pre-trained LLM with the custom dataset to build an on-premises AI chatbot.
• Optimized GPU resource management within Kubernetes to dynamically control Multi-Instance GPU (MIG).
• Implemented an automated workflow for Kubernetes to facilitate the deployment of applications across devices with a single-user interaction.