Hi, my name is
Lim Chee Kin.
AI Engineer & Solution Architect.
01. About Me
Hello! I'm Lim Chee Kin, a Senior Tech Lead, AI Engineer, and Solution Architect with a deep passion for AI engineering. I bring over 25 years of experience delivering advance software solutions by aligning business needs with technical design and implementation.
My expertise lies in architecting and implementing open-source AI, local AI infrastructure, and data sovereignty solutions, particularly for mobile-first web applications. I'm dedicated to building and leading teams to innovate with privacy-preserving and democratized AI.
I am committed to standardizing processes, driving innovation in the AI space, and continuously exploring new frontiers in technology.
Here are a few technologies I've been working with recently:
- AI Engineering
- RAG Systems
- LLM Integration
- Python
- Java
- Gemini API
- Docker
- AWS
▹ Work Experience
AI Engineer & Solution Architect @ RAG.WTF & AI Initiatives
2021-01 - Present
- Launched the Project Concord, a TypeScript-based, Dockerized Model Context Protocol (MCP) server that bridges modern AI agents with legacy databases by translating ambiguous schemas into clear, AI-friendly interfaces.
- Championed and developed open-source AI solutions focusing on data ownership, privacy, and efficient local AI processing; architecting and building RAG.WTF as a platform for secure, personalized knowledge discovery and management.
- Engineered 'open-text-embeddings', a Python library providing an OpenAI-compatible API for diverse open-source sentence transformer models, enabling significant cost reduction and eliminating vendor lock-in.
- Developed 'Talk To AI' application, integrating HuggingFace's FastRTC for low-latency real-time voice AI interactions; engineered a flexible backend supporting local and cloud-based STT, LLM, and TTS APIs.
- Pioneered and operationalized a self-hosted AI infrastructure (Coolify, Docker), running multiple local LLMs (Llama 3.2, DeepSeek-R1, etc.) and STT/TTS for data privacy and operational control.
- Advocated for and implemented robust data sovereignty by integrating embedded database solutions like SurrealDB.wasm with RAG.WTF.
- Strategically utilized TensorDock and Modal for scalable cloud GPU servers and serverless execution AI/ML workloads, complementing local AI capabilities.
- Previously initiated Talking Book YouTube channel (AI-powered summaries and Telegram bot) and Fluwix (Flutter showcases).
Senior Java Tech Lead @ DXC Technology
2013-01 - 2020-12
- Led a 6-developer international team (China, Europe, Malaysia) to deliver the Analytic Console for the Agile Process Automation (APA) platform (VueJS, Spring Boot, GoLang, MongoDB, AWS), contributing millions to company revenue.
- Headed a 5-developer international team (US, Malaysia) to create the EPIC Configurator for internal Enterprise Invoice Processing (JQuery UI, Grails Framework, Oracle DB), significantly streamlining configuration processes.
- Implemented a Divestiture and Acquisition (DnA) dashboard (AngularJS, Jersey, Spring, MongoDB, AWS) for critical real-time data insights supporting strategic executive decision-making.
- Prototyped an Intelligent Voice Agent (Conversational AI) leveraging Amazon Connect, AWS Lambda, Amazon Lex, Dialogflow, and Micronaut Framework.
Senior Java Tech Lead @ Zurich Technology Services Malaysia
2012-01 - 2013-12
- Led a 5-member production support and development team for motor and property claims systems (IBM WebSphere, FileNet, DB2, Spring, GWT, Hibernate/JPA).
- Resolved over 60 critical production issues within weeks, dramatically improving system stability and user satisfaction.
02. Some Things I've Built
Featured Project
RAG.WTF: Private Knowledge Platform
Architected and built RAG.WTF, an open-source platform for private, personalized knowledge discovery and management. Focuses on data ownership, privacy, and efficient local AI processing, integrating SurrealDB.wasm for data sovereignty.
- Open Source
- RAG
- Data Privacy
- Local AI
- Cloud AI
- surrealdb.wasm
- Flutter
- Dart
Featured Project
TelegramGPT: AI Telegram Bot
A Telegram bot powered by Google Gemini's API (Vertex AI / Google AI Studio). This bot leverages PostgreSQL for persistent conversation history and can integrate with self-hosted Speech-to-Text (STT) and Text-to-Speech (TTS) services.
- Open Source
- Telegram Bot
- Local AI
- Cloud AI
- Python
- Gemini API
- PostgreSQL
- TTS
- STT
Featured Project
open-text-embeddings Python Library
Engineered 'open-text-embeddings', a Python library providing an OpenAI-compatible API for diverse open-source sentence transformer models (e.g., BGE, E5). Enables significant cost reduction and eliminates vendor lock-in for embedding generation.
- Open Source
- Python
- Text Embeddings
- Sentence Transformers
- OpenAI-compatible API
- NLP
Featured Project
Talk To AI: Real-time Voice AI
Developed 'Talk To AI', an application integrating HuggingFace's FastRTC for low-latency (<300ms) real-time voice AI interactions. Features a flexible backend supporting local (LocalAI, Whisper.cpp, Llama.cpp) and cloud-based STT, LLM, and TTS APIs (Groq, Microsoft Edge).
- Open Source
- Voice AI
- FastRTC
- HuggingFace
- STT
- LLM
- TTS
- LocalAI
- Groq API
- Python
- FastAPI
03. Writing
-
AI is Ready. Your Legacy Database Isn't. Let's Fix That.
Project Concord is a high-performance, TypeScript-based MCP server designed to help AI systems work smoothly with older business databases by turning messy and unclear data into clean, reliable information.
Article · MCP, Legacy Systems
-
Building Your First No-Code MCP Server: The Fabric Integration Story
How I created a Model Context Protocol (MCP) server for Fabric REST API without writing a single line of code
Article · MCP, Fabric
-
Talking Book: Making Books Less Boring
I created Talking Book to make reading more engaging and accessible, especially for my 9-year-old son with dyslexia.
Article · YouTube, Telegram
04. Get In Touch
What's Next?
My inbox is always open for AI discussions, collaborations, or just to connect. Whether you have a question about RAG, local AI, open-source initiatives, or AI engineering in general, I'll do my best to get back to you!