Machine Learning Computer Science

Nguyen Van Manh Cuong

070******* # *****.*************@*****.***

ï https://www.linkedin.com/in/nungu/ § https://github.com/CuongWao123 Objective

Final-year Computer Science student with a strong foundation in machine learning, deep learning, and data-driven system design. Passionate about developing intelligent solutions that address real-world problems and enhance user experiences. Eager to begin a career as an AI Engineer, where I can apply my academic knowledge to practical challenges, collaborate on impactful projects, and continue expanding my skills in AI model development, deployment, and optimization. Known for being detail-oriented, fast-learning, and committed to long-term growth in the fields of artificial intelligence and data science. Education

Ho Chi Minh City University of Technology - VNUHCM Oct 2022– Oct 2026 Computer Science, GPA 3.7/4.0

English Certificate: Toeic Listening and Reading 725/990. Achievements

HCMUT Academic Encouragement Scholarship:

Awarded in Semesters 1/2021–2022,2/2023–2024, and 1/2024–2025 SKILLS

• Programming Languages: SQL, Python, C++/C, R, Java.

• Technologies: Docker, HuggingFace, LangGraph, LangChain, Scikit-learn, Numpy, Pandas, Flowise, N8N.

• Databases: MongoDB, PostgreSQL, MySQL, SQL Server.

• Concepts: Web Development, Data Structures & Algorithms, Big Data, Distributed Systems, AI Model Fine-tuning, Retrieval-Augmented Generation (RAG), AI Agents, Prompt Engineering, Machine Learning, Deep Learning, ETL Pipelines, Data Warehousing.

• Soft Skills: Teamwork, Presentation, Communication, Public Speaking. Experience

AI Engineer Intern - TMA Solutions Mar. 15, 2025 – Present Ho Chi Minh City, Vietnam

• Fine-tuned large language models using Hugging Face Transformers for various domain-specific applications.

• Designed and implemented a Retrieval-Augmented Generation (RAG) architecture and developed a multi-agent agentic system using LangGraph, LangChain, enabling automation of key processes, reducing staffing needs in certain roles, and improving user response efficiency .

• Built modular AI workflows using no-code/low-code platforms like Flowise and n8n,which reduced development time and empowered non-technical teams to prototype AI-driven features.

• Designed and maintained scalable data pipelines using Apache Kafka, Pulsar, Flink, and Spark for real-time data processing, supporting millions of daily events and enabling near real-time model updates, improving system adaptability.

• Tech Stack: Python, Java, Apache Flink, Apache Pulsar, Apache Spark, Apache Kafka, Hugging Face, Flowise, n8n, LangChain, LangGraph.

Projects

Customer Churn Prediction (Machine Learning Project) Jul. 2025

• Developed a machine learning pipeline to predict telecom customer churn on a 7,000+ row dataset using Logistic Regression and XGBoost, achieving up to 85.9% ROC-AUC and 81.5% accuracy.

• Performed in-depth EDA to extract business insights and inform feature engineering—e.g., tenure binning, service counts, interaction terms—boosting model performance.

• Tackled class imbalance with SMOTE, improving recall on the minority (churn) class from 54% to 81%, enhancing detection of high-risk customers.

• Designed a robust evaluation framework: ROC curves, precision-recall tradeoffs, and confusion matrix visualization using Matplotlib and Seaborn.

• Delivered insights for business stakeholders, highlighting key churn drivers (e.g., short tenure, month-to-month contracts) and recommending retention strategies.

• Tech Stack: Python, Pandas, Scikit-learn, XGBoost, Imbalanced-learn, Matplotlib, Seaborn, Statistical Analysis

Streaming Data Pipeline (Personal Project) Mar. 2025 - Apr. 2025

• Designed and implemented a real-time streaming data pipeline using Apache Kafka, Apache Spark, and PostgreSQL.

• Ingested data from public APIs into Kafka topics with fault-tolerant mechanisms.

• Transformed and processed data using Spark before storing in PostgreSQL for querying.

• Built real-time dashboards using Metabase to visualize streaming analytics.

• Tech Stack: Apache Kafka, Apache Spark, PostgreSQL, Metabase, API Integration. HCMUT Printing System Oct 2024 – Dec 2024

Team Project - 7 members

• Developed a smart printing system to modernize and optimize traditional printing services at HCMUT.

• Improved efficiency by reducing user wait times and enabling integration with existing campus systems.

• Strengthened adaptability and collaboration skills by responding to user feedback and iterative changes.

• Tech Stack : Spring Boot, ReactJS, MySQL, AZURE server.

• Roles: Team leader, Backend Developer, Database Developer.

• Key Contributions:

• Built RESTful APIs for file uploads, print job management, and statistical reporting.

• Designed a relational database schema in MySQL and implemented it using SQL.

• Deployed the backend on Azure cloud services.

Contact this candidate