Data Science Machine Learning

Data Scientist – AI/ML Engineer

NGUYEN THAI THONG

+84-825****** ***************@*****.***

LinkedIn Github

Ho Chi Minh, Vietnam

About

As a final-year Data Science student at the University of Science, VNU-HCM, I am passionate about AI/ML Engineering and eager to apply my skills to drive innovation. My goal is to leverage advanced technologies and data insights to make a meaningful impact. Committed to continuous learning, I aim to enhance my expertise and contribute to cutting-edge solutions in AI/ML. Ready to bring fresh perspectives, dedication, and collaboration, I am confident that my skills will be valuable assets in achieving shared goals and driving organizational growth. Education

BACHELOR OF DATA SCIENCE – University of Science – Ho Chi Minh, Vietnam October 2020 – Present

• Faculty: Bachelor of Mathematicals and Computer Science

• Majors: Data Science

• GPA: 3.64/4

• Relevant courses: Data Structures and Algorithms, Machine Learning, Advanced Machine Learning, Data Mining, Artificial Intelligence, Database Management Systems, etc. Technical Skill

• Programming Skills: Python, SQL, MATLAB, R,

C/C++

• Machine Learning: Predictive Modeling,

Classification, Clustering Models

• Deep Learning: CNN, RNN, Transformers,

Yolo, Large Language Model

• Web Scrawling: Selenium, BeautifulSoup

• Python Framework: Pytorch, Keras,

Tensorflow, LlamaIndex, OpenCV

• Other Skills: Excel, Word, PowerBI

Projects

REAL TIME FISHEYE CAMERA YOLOV9 – Thesis – Ho Chi Minh City, Vietnam May 2024 Description: Improved YOLOv9 for fisheye camera object detection and 360-degree images. Key Contributions:

• Processed and split training and validation datasets.

• Trained the model using hyperparameter tuning and specific configurations to optimize performance.

• Conducted and synthesized previous research, especially studies on Deformable ConvNets v2 and Large Selective Kernel, to develop our model.

• Developed a practical application on Hugging Face Spaces to demonstrate the model. Programming languages and technologies: Python, Pytorch, Gradio, Hugging Face, Seaborn. SENKU CHATBOT– Personal Project – Ho Chi Minh City, Vietnam January 2024 – Ongoing Description: Developed an advanced LLM assistant powered by GPT-3.5 within a RAG pipeline. Key features include:

• Used RAKE (Rapid Keyword Extraction Algorithm) from NLTK to identify key terms from user queries.

• Built a scraper with Arxiv API and PyPDF2 to retrieve and read relevant PDFs.

• Utilized LlamaIndex with a "tree_summarizer" query engine to generate accurate and comprehensive responses.

Programming languages and technologies: Python, LlamaIndex, Streamlit, Arxiv API. SKIN CANCER CLASSIFICATION – Personal Project – Ho Chi Minh City, Vietnam December 2023 Description: A personal project to classify skin cancer using deep learning models on a public dataset. Key features include:

• Implemented various models including VGGNet, MobileNet V3, EfficientNet B3, and an Ensemble Model.

• Conducted comparative analyses to evaluate each model's accuracy, sensitivity, and specificity, identifying the most effective approach for skin cancer classification Programming languages and technologies: Python, Pytorch, Matplotlib. Cetifications

SQL (ADVANCED) – Hacker rank October 2023

DATA ANALYTICS ESSENTIALS – Cisco October 2023

SQL (INTERMEDIATE) – Hacker Rank August 2023

ENGLISH– Toeic LR (820/990) January 2024

Contact this candidate