Nguyen Quang Khai

Hello, I'm Nguyen Quang Khai

I am a |

Get in Touch

About Me

I'm a Computer Science student at FPT University of Ho Chi Minh City, passionate about AI and data-driven solutions. With expertise in Python, deep learning and machine learning frameworks, I have contributed to projects in data analysis, recommendation systems, and multimodal AI. I'm eager to collaborate on innovative projects and solve real-world challenges.

Full Name: Nguyen Quang Khai

Date of Birth: January 06, 2004

Gender: Male

Location: Ho Chi Minh City, Vietnam

Phone: +84 976 504 711

Email Me

GitHub

LinkedIn

Facebook

TikTok

Education

FPT University, Ho Chi Minh City

09/2022 - Present | Major: Computer Science

GPA: 3.5/4.0 | 7 of 9 semesters completed

Received scholarships for academic excellence

University of Wollongong, Malaysia

09/2022 - 01/2023 | Grade: Good

Completed a 4-month English language course at the University of Wollongong, Malaysia.

Experience

Artificial Intelligence Engineer Intern

Jul 2025 – Present | DFM-Europe, Ho Chi Minh City, Vietnam

  • Led development of a custom RAG-based chatbot for enterprise LLM prompt automation, built fully from scratch.
  • Designed retrieval pipelines with LangChain, LangSmith, and LangGraph; logged metrics for evaluation on in-house datasets.
  • Measured retrieval performance using Precision, Recall, MRR, and nDCG; assessed generation with Faithfulness and Groundedness.
  • Optimized retrieval with multi-query expansion and fine-tuned bi-/cross-encoder models.

Machine Learning Engineer Intern

Feb 2025 – Jul 2025 | HRS Group, Ho Chi Minh City, Vietnam

  • Developed an OCR-based AI system to extract structured information from hotel invoices.
  • Applied Transfer Learning techniques for domain-specific invoice recognition (CPV format).
  • Integrated Named Entity Recognition (NER) using BERT-based large language models to identify key entities.
  • Implemented semantic search and retrieval using vector databases for validation and downstream analytics.
  • Designed and fine-tuned models with LoRA/QLoRA for preprocessing tasks, enabling efficient data cleaning and automated labeling.

Research Assistant

Aug 2024 – Jan 2025 | National Chung Cheng University, Chiayi City, Taiwan

  • Conducted in-depth research in Computer Vision, assisting MSc and PhD students in project development.
  • Improved a lightweight head pose estimation model (0.66M parameters), optimizing Gaussian-distributed sampling to reduce RMSE.
  • Six-month fully funded research internship under the TEEP scholarship by the Taiwanese Government.
  • Highlighted the role of data distribution strategy in optimizing lightweight model performance.

Research and Projects

RAG Chatbot for Vietnamese Traffic Laws

Retrieval-Augmented Generation from scratch

2025 | Production-ready Retrieval-Augmented Generation chatbot built from scratch with hybrid search, FastAPI backend, Qdrant vector DB, and LangGraph workflow integration.
Rare Label Detection for Email Classification

Rare Label Detection for Email Classification

2025 | Algorithm to surface rare/noisy samples in enterprise email datasets using embedding, dimensionality reduction (UMAP), clustering (HDBSCAN), and Isolation Forest, reducing manual labeling effort by ~90%.
Head Pose Estimation with Gaussian Sampling

Head Pose Estimation – Gaussian Sampling

2024 | National Chung Cheng University.
Enhanced lightweight head pose estimation (0.66MB) using Gaussian-based reference image sampling, improving accuracy while maintaining real-time edge deployment capabilities.
Email Reranker API

Email Reranker with FastAPI and Postman

2025 | API to parse and chronologically reorder raw email threads (.eml) using Talon, aiohttp, and Docker for enterprise email management.
Pysvgenius - Text & Image to SVG

Pysvgenius - Text & Image to SVG

2025 | Text & Image ➜ Optimized SVGs | Smart resizing & conversion for AI, web, and design projects.
LLM to SQL for Hospital Database Queries

LLM to SQL for Hospital Database Queries

2025 | Developed a system converting natural language queries into SQL for hospital databases using LLMs, enabling accurate and efficient data retrieval for healthcare analytics.

Awards & Recognitions

FPT University Scholarship

Awarded 70% scholarship for the entire 4-year program

Good Student for All Semesters

Maintained GPA > 8.0 for each semester

FPT Paper Presentation Award – Computer Science

Recognized for outstanding research presentation in Computer Science

Certifications

Deep Learning Certificate

Coursera — View Certificate

Focused on neural networks, CNNs, and deep learning fundamentals.

TOEIC Certificate

Score: 750 — English Proficiency

Demonstrates strong English reading and listening skills.

Big Data Certificate

Coursera — View Certificate

Covers data processing, analysis, and visualization techniques.

AI Foundations for Everyone Certificate

Coursera — View Certificate

Introduces AI concepts and practical applications.

Ethics in the Age of AI Certificate

Coursera — View Certificate

Focuses on ethical considerations in AI development and usage.

Software Development Lifecycle Certificate

Coursera — View Certificate

Covers SDLC processes, project management, and software quality.

Skills

  • Python (Automation, Scripting), Java, JavaScript, SQL, HTML5, CSS3
  • FastAPI, Docker, Postman, HTTP, Jupyter
  • MySQL, Microsoft SQL Server
  • Machine Learning & Deep Learning: Scikit-learn, PyTorch, TensorFlow, Hugging Face, RAG, LlamaIndex, LangChain
  • Data Engineering & Pipelines: LangGraph, MLflow, Pandas, NumPy
  • Data Visualization: Matplotlib, Seaborn
  • Tools: Git, Google Colab, Docker

Contact Me