I am a versatile AI and data engineering professional with extensive experience designing and maintaining end-to-end data pipelines. I have built systems to ingest and integrate data from sources like Excel, PostgreSQL, SQL Server, and Oracle, using Python and Kafka to ensure scalability and reliability. I’ve implemented both scheduled and event-driven workflows, exposed centralized data via APIs, and monitored system performance with tools like Nagios. Additionally, I have hands-on experience in data governance, including metadata enrichment, authority-based access control, and ensuring compliance with internal and external policies. On the AI and software side, I have developed internal chatbot systems, evolving from rule-based and retrieval-based solutions to LLM-powered Retrieval-Augmented Generation (RAG) architectures. I handled document preprocessing, embedding generation, deployment, and continuous improvement based on user feedback. I am also a full-stack developer, skilled in React, Vue, or Svelte with TypeScript, FastAPI backends, and CI/CD pipelines using GitLab, Jenkins, and ArgoCD. I deploy containerized applications on Kubernetes/OpenShift and monitor system resources to ensure performance and reliability. I thrive at the intersection of data, AI, and software development, delivering solutions that are both technically robust and business-aligned.

Chin Chee Yuan

I am a versatile AI and data engineering professional with extensive experience designing and maintaining end-to-end data pipelines. I have built systems to ingest and integrate data from sources like Excel, PostgreSQL, SQL Server, and Oracle, using Python and Kafka to ensure scalability and reliability. I’ve implemented both scheduled and event-driven workflows, exposed centralized data via APIs, and monitored system performance with tools like Nagios. Additionally, I have hands-on experience in data governance, including metadata enrichment, authority-based access control, and ensuring compliance with internal and external policies. On the AI and software side, I have developed internal chatbot systems, evolving from rule-based and retrieval-based solutions to LLM-powered Retrieval-Augmented Generation (RAG) architectures. I handled document preprocessing, embedding generation, deployment, and continuous improvement based on user feedback. I am also a full-stack developer, skilled in React, Vue, or Svelte with TypeScript, FastAPI backends, and CI/CD pipelines using GitLab, Jenkins, and ArgoCD. I deploy containerized applications on Kubernetes/OpenShift and monitor system resources to ensure performance and reliability. I thrive at the intersection of data, AI, and software development, delivering solutions that are both technically robust and business-aligned.

Available to hire

I am a versatile AI and data engineering professional with extensive experience designing and maintaining end-to-end data pipelines. I have built systems to ingest and integrate data from sources like Excel, PostgreSQL, SQL Server, and Oracle, using Python and Kafka to ensure scalability and reliability. I’ve implemented both scheduled and event-driven workflows, exposed centralized data via APIs, and monitored system performance with tools like Nagios. Additionally, I have hands-on experience in data governance, including metadata enrichment, authority-based access control, and ensuring compliance with internal and external policies.

On the AI and software side, I have developed internal chatbot systems, evolving from rule-based and retrieval-based solutions to LLM-powered Retrieval-Augmented Generation (RAG) architectures. I handled document preprocessing, embedding generation, deployment, and continuous improvement based on user feedback. I am also a full-stack developer, skilled in React, Vue, or Svelte with TypeScript, FastAPI backends, and CI/CD pipelines using GitLab, Jenkins, and ArgoCD. I deploy containerized applications on Kubernetes/OpenShift and monitor system resources to ensure performance and reliability. I thrive at the intersection of data, AI, and software development, delivering solutions that are both technically robust and business-aligned.

See more

Experience Level

Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Intermediate
Intermediate
Intermediate
Intermediate
Intermediate
Intermediate
Intermediate
See more

Language

English
Fluent

Work Experience

AI Software Engineer at MITAC Holdings Corporation (MITAC Holdings)
January 1, 2021 - January 1, 2025
Designed, implemented, and maintained in-house AI-powered chatbot systems, evolving from rule-based and retrieval-based solutions to LLM-based Retrieval-Augmented Generation (RAG) architectures to support enterprise knowledge access. Integrated large language models using LangChain including prompt templates, parameter tuning, and retrieval-logging optimization; preprocessed and managed internal unstructured data for AI applications (data cleaning, text chunking, embedding generation, and vector storage with ChromDB). Deployed AI-enabled applications to production environments and iteratively improved system performance based on logged conversations and user feedback. Built backend services using FastAPI to integrate AI models and data services into existing internal platforms. Built full-stack web apps using TypeScript with React, Vue, and Svelte to deliver AI-enabled and automation-focused internal tools. Integrated AI services and APIs into business apps, including internal ChatGPT-

Education

Master of Computer Science (Artificial Intelligence) at University of Nottingham, UK
January 1, 2025 - February 5, 2026
Bachelor of Resources Engineering at National Cheng Kung University, Taiwan
January 1, 2017 - January 1, 2021

Qualifications

Add your qualifications or awards here.

Industry Experience

Software & Internet, Media & Entertainment