tn.Thien Nguyen
EN/VI
Thien Nguyen

AI SYSTEMS — SOFTWARE ENGINEERING

Thien Nguyen

I build AI systems, model deployment tools, and software.

Based in Ho Chi Minh City, Vietnam

I build useful AI and software from messy technical questions—and explain the decisions so people can trust and use the result.

Selected work

LLM deployment, knowledge retrieval, and GPU computing.

InferCap, Healthcare GraphRAG, and CUDA Autoencoder: hardware checks, information retrieval, and compute optimization.

RESEARCH PROJECTS

Visual question answering and computer vision.

TECHNICAL FOCUS

AI systems, ML infrastructure, and software.

My work covers information retrieval, model configuration and benchmarking, CLI tools, and web interfaces.

RESEARCH EXPERIENCE

Infographic question answering and image analysis.

My academic projects include Vietnamese infographic question answering and facial landmark localization. They connect computer science with dataset preparation, model exploration, and evaluation.

2025

ViInfographicsVQA

Team project covering Vietnamese infographic data, question–answer pairs, model exploration, and a Streamlit / FastAPI demonstration.

2025

Facial landmark localization

Research exploration covering related work, FaceXFormer, smaller-dataset experiments, and evaluation notebooks.

Now

Building in public

Developing a clearer home for technical projects, learning notes, and the decisions behind each piece of work.

2025

A RAG Approach for Multi-Modal Open-ended Lifelog Question-Answering

Peer-reviewed ICMR 2025 paper on OpenLifelogQA, a 14,187-question dataset, and a retrieval-augmented generation pipeline for multi-modal lifelog question answering. Co-author.

ABOUT THIEN NGUYEN

Nguyen Van Minh Thien

AI systems & software engineer.

I build AI systems and software, with attention to the whole trail of a project: framing the question, testing an approach, documenting the limits, and making the result easy to explore. I also enjoy sharing programming and mathematics through explanations, examples, and exercises.

View projects

↗CONTACT

Have a technical idea worth making useful?

I’m open to full-time and contract opportunities in AI systems, ML infrastructure, and research engineering. Reach out through LinkedIn or email.