Machine Learning Data Science

Nguyen Manh Tuan

Final-year Data Science student at HUFLIT with strong interest in Artificial Intelligence, Natural Language Processing (NLP), and Computer Vision. Skilled in developing, training, and deploying ML/DL models with Python and modern AI frameworks.

# *******************@*****.*** § github.com/nguyenmanhtuan2004 Ho Chi Minh City, Vietnam Projects

MathQA MAS – NLP Benchmarking System May 2025 – Aug 2025

• Built an end-to-end question answering system combining Zero-shot, Chain-of-Thought, Program-of-Thought, and Program-aided Language Models.

• Integrated LangSmith to create datasets, track experiments, and benchmark models across GSM8K, TATQA, and TABMWP.

• Designed evaluators for accuracy, cost, latency, and error analysis – enabling optimization and comparative reports.

• Built Multi-Agent system with LangChain and GPT models achieving 0.67% to 1% accuracy improvement across 3 mathematical reasoning datasets

• GitHub: MathQA MAS

Plant Disease Detection – Computer Vision Sep 2024 – Nov 2024

• Applied CNNs with data augmentation to detect plant diseases from leaf images.

• Converted trained models to TensorFlow Lite for mobile/embedded deployment.

• Evaluated performance with accuracy, confusion matrix, and classification report.

• GitHub: Plant Disease Detection

Breast Cancer Detection – Structured Data Analysis Dec 2024 – Feb 2025

• Conducted preprocessing, normalization, and missing-value handling on medical datasets.

• Trained ML models (Logistic Regression, SVM, Random Forest) for binary classification.

• Evaluated with Accuracy, Precision, Recall, and F1-score; deployed via Streamlit for interactive demo.

• GitHub: Breast Cancer Detection

Education

Ho Chi Minh City University of Foreign Languages and Information Technology 2022 – Present Major: Information Technology (Data Science)

GPA: 3.37 / 4.00

Skills

Programming: Python, Java, C++, C#

AI/ML: NLP, Computer Vision, Transformers (Hugging Face), PyTorch, TensorFlow, Keras, Scikit-learn Data Processing: Pandas, SQL, Data Cleaning, Feature Engineering Visualization/Tools: Matplotlib, Power BI, Git, FastAPI, Kafka, LangChain, LangSmith Languages

English: Good at reading and understanding technical documents. 1

Contact this candidate