Building the frontier of AI — from LLM-powered multi-agent systems and RAG architectures to enterprise-grade ML infrastructure deployed at scale on AWS and Azure.
I'm Nguyen Quang Phu, an AI Engineer at FPT Software AI Center with hands-on experience building and deploying AI-powered applications — specialising in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Agentic AI systems.
I design end-to-end ML solutions that bridge model training, backend engineering, cloud deployment, and production support. I enjoy solving hard problems at the intersection of research and real-world enterprise impact.
Proficient in building enterprise dashboards with real-time monitoring and analytics. Experienced with scalable system architecture and production-grade pipelines on AWS Bedrock and Azure AI Services.
Building production AI systems at enterprise scale — from research to live deployment.
A full-stack AI toolkit — from model training to production deployment.
Strong theoretical foundation in AI and Computer Science from Vietnam's top engineering university.
ML/DL projects from coursework and independent research at HCMUT.
April 2025 · Team of 5
Implemented and compared multiple ML/DL models — Decision Trees, Naïve Bayes, SVM, XGBoost, Random Forest, MLP, and Bi-LSTM. Focused on feature transformation, high-dimensional data handling, hyperparameter tuning, and systematic model evaluation.
April 2025 · Team of 5
Fine-tuned pre-trained language models for sentiment analysis, question answering, and machine translation. Implemented and compared T5-Base, BART-Base, and Flan-T5-Small — assessed accuracy, efficiency, and resource trade-offs with full GPU acceleration.
December 2024 · Team of 3
Evaluated SVM, Random Forest, XGBoost, Neural Networks, and Distilled BERT for AI text classification in the educational domain. Analysed model performance detecting LLM-generated essays with focus on accuracy and generalisation.
Continuous learning across leading AI, cloud, and ML platforms.
Whether it's a new AI project, a research collaboration, or a full-time role — I'd love to connect.