ViInfographicsVQA
Team project covering Vietnamese infographic data, question–answer pairs, model exploration, and a Streamlit / FastAPI demonstration.
AI SYSTEMS — SOFTWARE ENGINEERING
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
InferCap, Healthcare GraphRAG, and CUDA Autoencoder: hardware checks, information retrieval, and compute optimization.
Open-source developer tool — 2026
A CLI toolkit for LLM inference preflight, serving configuration, deployment verification, benchmarking, telemetry, and capacity analysis.
LLM inference toolingOpen case studyApplied AI systems project — 2025
A healthcare GraphRAG system combining semantic retrieval with structural search over a medical knowledge graph.
GraphRAG / Applied AI / HealthcareOpen case studyParallel programming final project — 2025
A CIFAR-10 autoencoder with unified CPU and CUDA GPU pipelines, including naive GPU V1 and optimized GPU V2 kernels.
CUDA / GPU Systems / PerformanceOpen case studyRESEARCH PROJECTS
Course project · 2025 — 2025
A Vietnamese infographic question-answering project that follows the path from visual data to a working web demo.
Multimodal AI / VietnameseOpen case studyResearch exploration — 2025
A computer vision study that turns a FaceXFormer survey into experiments, notebooks, and a documented evaluation path.
Computer Vision / FaceXFormerOpen case studyTECHNICAL FOCUS
My work covers information retrieval, model configuration and benchmarking, CLI tools, and web interfaces.
Agentic AI, retrieval, and knowledge graphs for systems that can act and answer from knowledge.
Hardware checks, model serving configuration, benchmarking, and inference telemetry.
CLI workflows, endpoint verification, automation, and interfaces that make systems usable.
RESEARCH EXPERIENCE
My academic projects include Vietnamese infographic question answering and facial landmark localization. They connect computer science with dataset preparation, model exploration, and evaluation.
Team project covering Vietnamese infographic data, question–answer pairs, model exploration, and a Streamlit / FastAPI demonstration.
Research exploration covering related work, FaceXFormer, smaller-dataset experiments, and evaluation notebooks.
Developing a clearer home for technical projects, learning notes, and the decisions behind each piece of work.
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
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
I’m open to full-time and contract opportunities in AI systems, ML infrastructure, and research engineering. Reach out through LinkedIn or email.