Do Hoang Vu
AI Engineer
Hoang Van Thu Street
Ho Chi Minh City, Phu Nhuan District
Vietnam
Education
The Saigon International University
Bachelor of Artificial Intelligence
Expected graduation: 2027
GPA: 3.62/4.00
Certifications
Machine Learning - Deep Learning Foundation
cole.vn
Exploratory Data Analysis for Machine Learning
IBM - Coursera
Machine Learning Specialization
Stanford - Coursera
Machine Learning Specialization
Stanford Online - Coursera
Languages
Selected Projects
Ready4RAG: High-Precision Dual-Layer RAG Pipeline
personal project • 01/2026 → 02/2026 • Lead Developer
A next-generation ingestion system converting complex PDFs into value using Vision LLMs and Hybrid Memory (Vector + Graph) for grounded, high-precision answers.
AcaRead: AI-Powered Academic Assessment System
team project • 03/2025 → 12/2025 • Technical Lead
An advanced educational platform that transforms academic papers (PDFs) into interactive IELTS-style reading exams using Gemini 2.5 Flash, bridging passive reading and active comprehension assessment.
TwinSelf - Digital Twin Chatbot
personal project • 09/2024 → 12/2024 • Lead Developer
A sophisticated RAG-based chatbot system using a triple-memory architecture (Semantic, Episodic, Procedural). This system serves as the intelligence behind the AI Chatbot on this portfolio, providing an authentic digital twin experience.
Face Attendance: Kiosk-Based Recognition & Anti-Spoofing
personal project • 11/2025 → 12/2025 • AI/Vision Engineer
A modular kiosk-based face recognition system for attendance and access control, featuring facial alignment, quality gating, and anti-spoofing mechanisms for near real-time biometric verification.
Competitions
- 10/2025 → 12/2025
Viettel AI Race 2025
Top 5 in Round 1
Competed solo in the NLP track of Viettel AI Race 2025, building a pipeline for complex PDF table extraction, numerical data retrieval, and multiple-choice QA. Achieved Top 5 in Round 1 as a solo competitor among team-based entries.
- 09/2024 → 12/2024
AIC24 COMPETITION
Team Member
Developed scalable video understanding pipelines for event retrieval, leveraging contrastive learning and multimodal embeddings to enhance temporal-semantic alignment in untrimmed video datasets.
- 10/2023 → 12/2023
ZALO AI CHALLENGE 2023
Team Member
Built deep generative models for symbolic and audio-based music generation using Transformer-based architectures. Fine-tuned temporal coherence and structural consistency to align with evaluation metrics in generative audio tasks.
Technical Skills
LLM Frameworks
Vector & Graph Databases
LLM Frameworks
MLOps / LMOps
Backend
Soft Skills
- •Research communication & scientific writing
- •Experiment design and evaluation
- •Collaborative coding & version control (Git workflow)
- •Critical problem solving & analytical thinking
- •Technical documentation & knowledge sharing