Machine Learning Data Engineer
Resume:
Nguyen Khac Huy
Binh Duong
******.***@*****.***
Khac Huy Nguyen LinkedIn
github.com/ngkhuy
OBJECTIVE
Seeking a full-time opportunity as AI Developer, Data Engineer to gain practical experience and improve skills in machine learning and deep learning. Passionate about using AI to drive innovation and improve business outcomes, eager to contribute to dynamic AI projects.
Develop problem-solving skills, learn new technologies with desire to contribute to the team.
SKILLS
Programming Languages: Python, Java, C, JavaScript, HTML, CSS
AI/ML Frameworks & Libraries: Pytorch, TensorFlow, Keras NLTK, Pandas, Scikit-learn, Matplotlib, OpenCV, Hugging Face
Web Frameworks: FastAPI, Django, NodeJS, Apache
Programming Techniques: OOP, Data Structures & Algorithms
Database: SQL, Microsoft SQL Server, PostgreSQL
Cloud/IoT Services: AWS, ThingSpeak (IoT)
API & Testing Tools: Postman
Design & Prototyping Tools: Draw.io, Figma (Basic)
Project Management: Git, GitHub
Operating System: Windows, Ubuntu (Linux)
EDUCATION
Ton Duc Thang University, Ho Chi Minh City, Vietnam [October 2021 – Present] School of Computer Information Technology
Major: Computer Science
Key Subjects: Machine Learning, Deep Learning, Natural Language Processing, Big Data, Web Development
PROJECTS EXPERIENCE
Project Title: HEALTH CARE WEBSITE
Dates: May 2025 - Present
Description: A website platform for a customer health center. Allow people login, sign-up, booking schedules for medical examination. Intergration generation bills, payment methods, deep learning model chatbot from “Medical bot with transformer” project, heart disease prediction form in reference.
Tech Stack: AI Architecture: Medical bot with Transformer and GPT project. Front-end: HTML, CSS, JS
Back-end: NodeJS, FastAPI
Database: PostgreSQL, Hugging Hub (AI model)
Cloud Service: AWS S3
Role: AI Developer, Full-stack Developer
Results: On process. Complete homepage, login, sign-up function from FE to BE logical. Project Title: MEDICAL BOT WITH TRANSFORMER AND GPT HEART DISEASE DETECTION WITH MACHINE LEARNING
Dates: March – June 2025
Description: Build deep learning models from scratch with Transformer and GPT architectures. Models learn from trusted medical dataset in Vietnamese which was collected on e-doctor and vinmec forums. Using Pyte Pair Encoding technique to process dataset for high accuracy purpose.
In addition, training machine learning models with TF built-in libraries training on UCI Heart disease dataset. Process dataset with EDA task to get data’s insight. Tech Stack: AI Architecture: Transformer architecture and GPT architecture with Pytorch. TensorFlow for machine learning models.
Database: Drive
Role: AI Developer
Results: Archieve hight scores in BLEU and F1 for medical bot model, over 85% accuracy and others. Generate answers that can be referenced, with a high similarity rate to the answers found on the Internet.
Project Title: UNVERIFY NEWS CLASSIFICATION
Dates: January – February 2025
Description: Crawling raw data from Internet news websites, pre-process dataset and use doc2vec technique to create vector database. Implement LSTM models from scratch for learning processed dataset. Return labels for classify is verified news. Main features are labeled and confirmed by LLMs and Human. Tech Stack: AI Architecture: LSTM architecture with and without attention. Dataset: Crawl from VNExpress, Kenh14 and ZNews with Beautiful Soup (Python) Database: Drive
Role: AI Developer
Results: Return around 60 percent accuracy for unseen news and 80% for several training data. Lack of dataset and incorrect data feature filtering. Project Title: THIRD-PARTY WEBSITE FOR RENTING FARM LAND (IoT) Dates: September 2024 – March 2025
Description: Website platform connect farmers and customers, where people can rent farming land and control hardwares from distance in order to take care their farm. Allow citizens planting and taking care vegetables.
Tech Stack: Front-end: HTML, CSS, JS
Back-end: Python (Django), C/C++ (Hardwares control) Hardware: LCD, Humidity sensor, rain sensor, ESP32, Servo RC 360o, power supplier, sticks
Database: PostgreeSQL
Cloud Service: AWS
Role: Front-end Developer, Hardware Development
Results: Highly regarded from supervisor lecturer in final presentation. Completely build prototype with fully functions. Connect from website to database and control hardware succesfully.
Project Title: ENGLISH TRANSLATOR USING LSTM WITH ATTENTION Dates: March – June 2025
Description: Deep learning models base on RNNs, using hugging face large 250k+ dataset English to Vietnamese for learning. Build prototype for presentation to classes and lecturers. Tech Stack: AI Architecture: LSTM with Attention mask technique and non technique. Database: Drive, Hugging Face
Role: AI Developer
Results: Get high accuracy about under 80 percent. Completely generate translation with the same meaning with input sentences.
WORK EXPERIENCE
Personal Tutor [September 2022 – October 2024]
Tutored 15+ students in Mathematics, Physics, and Introduction to Programming
Fostered passion for STEM through hands-on projects with Scratch CERTIFICATIONS
Responsive Web Design – freeCodeCamp
Aptis ESOL International (C1) – British Council
INTERESTS & ACTIVITIES
Playing badminton
Reading novels
Traveling
Contact this candidate