Full-stack software engineer specialized in integrating Large Language Models into production-ready applications. Experienced in RAG pipelines, containerized microservices, and building AI-driven automation tools that solve real-world workflows.
About
I'm a full-stack software engineer with a deep focus on bringing Large Language Models from experimental prototypes into live, user-facing systems. My work spans the entire stack — from architecting RAG pipelines that ground LLM responses in real business data, to deploying high-throughput inference endpoints that serve thousands of requests with predictable latency.
Most recently at CTC Global, I built the bridge between legacy PHP monoliths and a modern Python AI service layer, cutting inference latency by 40% with vLLM and building internal RAG chatbots that transformed how support teams access institutional knowledge. At MIMOS Berhad, I engineered an end-to-end proposal analysis tool with Weaviate and MinIO, automating workflows that previously consumed days of manual review.
Skills
Experience
Education
Volunteering
Managed medal presentation and ceremony logistics during the event, coordinating with volunteers to ensure smooth athlete recognition.
Organised a university-wide LAN party, handling vendor negotiations, equipment logistics, and tournament scheduling for participants.
Contributed to event setup and dismantle operations, supporting one of Malaysia's largest annual running events.