PROJECTS
Built an automated content intelligence system that analyzes TikTok videos to extract insights including speech transcripts (Vietnamese/English), on-screen text, detected products/objects, and AI-generated summaries. Enables scalable video content analysis for market research and trend monitoring with a user-friendly web interface for configuration and real-time monitoring. TikTok Video AI Analysis Pipeline
EXPERIENCE
Seeking a Data Engineer position at a growth-oriented company where I can apply my technical expertise and build a long-term career.
CAREER
OBJECTIVE
EDUCATION Ho Chi Minh City University of Technology and Education
*********.****@*****.***
AI ENGINEER INTERN Ho Chi Minh City
Duong Minh Hieu
TELIT Technology Solutions Co., Ltd
Website Data Management Intern
9/2022 - Expected Graduation: 06/2026 Currently completing graduation thesis on TRIP BOT Major: Data Engineering
Relevant coursework: Big Data Analytics, Database Systems, Machine Learning, Cloud Computing
6/2025 - 9/2025
SKILLS Programming Languages: Python, C++, C#, SQL, Java, GDScript Tools & Platforms: Docker, Git, Godot, Firebase, Apache, Airflow, Kafka, Spark Data Processing & Machine Learning: Pandas, NumPy, and ML libraries such as Scikit-learn, TensorFlow, PyTorch. CNNs, RNNs, GANs and RAG.
ADDITIONAL
INFORMATION
Digital Content Creation: Managed and produced content for a Facebook fanpage
(70,000 followers) and a YouTube channel (25,000 subscribers), focusing on topics such as movies, anime, and gaming.
Tech Stack: Python, Apache Airflow, Docker, PostgreSQL, MinIO, OpenAI Whisper, YOLOv8, EasyOCR, Streamlit, yt-dlp
Built an NLP pipeline to extract component-level sentiment from 10K+ Nintendo Switch reviews using Word2Vec and BERT tokenization, identifying specific hardware strengths and weaknesses to inform product insights.
Nintendo Switch Review Analysis
Tech Stack: Python, Pandas, BERT, Word2Vec
AI chatbot providing Vietnamese game assistance using RAG architecture. Automated ETL pipeline processes documents into vector embeddings for semantic search, integrated with Gemini AI for intelligent responses.
PikaHelper - Vietnamese PokeMMO RAG Chatbot
Tech Stack: Python, FastAPI, Airflow, PostgreSQL, MinIO, Qdrant, Docker, Transformers Link Project Link Video
Link Project Link Video
Link Project Link Video
Developed a streaming system that crawls RSS feeds from 2 Vietnamese news sources every 60 seconds using multi-threaded scrapers, streams data through Kafka, and applies ML models for topic detection and sentiment analysis.
Real-time News Analytics Pipeline
Tech Stack: Apache Spark, Kafka, Airflow, MongoDB, Elasticsearch, Docker, Python Link Project Link Video