Pham Nguyen Hai Long
Ho Chi Minh, Hoa Hao st, District 10 |-|-
Linkedin: Long Pham | Github: CrispyChillies
SPECIALTIES
Machine Learning, Computer Vision, Large Language Model, Software Engineering.
EDUCATION
Sept 2022 – Sept 2026
Bachelor of Science, Informration Technology, University of Science, VNUHCM
• Major: Computer Vision
• GPA: 3.22/4.0
• Relevant Coursework: Machine Learning, Multivariate Data Analysis, AI Fundamentals, Data Structures &
Algorithms, Databases, Calculus, Linear Algebra, Probability & Statistics, Discrete Mathematics, Combinatorial
Mathematics, Computer Graphics, Digital Image & Video Processing, IoT.
• Languages: English (Ielts 7.0).
PROJECTS
2024 - Present
NoteUS- AI-powered Smart Notebook Platform
• Developed a web platform integrating Large Language Models (LLMs) to assist students in studying more
effectively. The website allows users to summarize learning materials, generate mind map cheat sheets, and
interact with an AI chatbot that answers questions based on uploaded documents.
• Fine-tuned Microsoft TrOCR model on a Vietnamese handwriting dataset to improve OCR performance for
handwritten text recognition. The model was integrated into a document processing pipeline to support
educational tools and applications.
• Tools Used: Python, LLMs, RAG, FastAPI, MilVus, Hugging Face, FastAPI, Docker
• Team size: 5
• Role: Project Lead & System Architect (RAG & LLM Integration)
E-commerce Website Project Link - Introduction To Software Engineer
Sept 2024
• A project in software engineering. I used TypeScript for the frontend, Express for writing APIs, and SQL for the
database running on Microsoft SQL Server. Learned to follow the SCRUM method to manage the project
efficiently and held weekly meetings to ensure timely completion.
• Tools Used: TypeScript, Express JS, SQL, ShadcnUI
• Team size: 5
• Role: Project Lead & Backend Developer
CALL - Project in HCMUS AI-Innovation Contest
Sept 2024
• Developed a video call application designed for the deaf as part of the HCMUS AI Innovation Contest with my
team. Built the web demo using Flask and implemented video calling functionality using Python socket
programming. Integrated an AI model based on Temporal Convolutional Networks (TCN) to support sign
language recognition, though the AI component remained incomplete due to model limitations.
• Tools Used: Python, Socket Programming, TCN Model
• Team size: 5
• Role: Backend Developer & AI Integration Support
Medical Question Extraction Tool
Dec 2024
• Developed an application using EasyOCR to extract text from multiple-choice questions in a medical practice
book. Processed the extracted data into an Excel file containing questions and four answer choices from the PDF.
Designed to help medical students efficiently create flashcards by importing the Excel file into Anki for studying.
• Team size: 1
• Tools Used: Python, EasyOCR, Docker, FastAPI
• Role: Backend Developer
RESEARCH
2024 - Present
SELab - Research on LLM Applications in Software Testing
• Conducting research on applying Large Language Models (LLMs) in software testing to optimize tester
workflows and improve testing efficiency. Focused on automating test case generation, bug detection, and report
summarization to reduce manual effort and enhance accuracy. The project aims to help companies optimize
costs and improve overall software quality.
• Tools Used: Python, LLMs, NLP, Software Testing Automation
Image Inpainting Research - Image Processing
Dec 2024
• A Project in Image Processing a subject of Computer Vision. We have to research and summarize all the state of
the art method for the inpainting problem, make comparison and choose the best method out of the list. Run
inference and evaluation on the chosen method.
• Tools Used: Google Colab, Python
PCL and its application in self driving vehicles - Computer Graphics
Dec 2024
• A project in Computer Graphics a subject of Computer Vision. We have to research about the PCL library, how to
call and use the functions in real programme. After that reporting all the information in a paper. We apply the
PCL application in self driving vehicles. PCL is collected via radar and we try to analyze the collected PCL to
recognize which PCL group is human and which is vehicles and make bounding box.
• Tools Used: PCL library, C++
EXPERIENCE
Sept 2024 - February 2025
Teacher Mentor, MindX Technology School
• Taught robotics, Scratch, Python app development, and web development to students aged 7 to 18.
• Designed interactive coding lessons to engage students and foster problem-solving skills.
• Guided students in hands-on projects, enhancing their understanding of programming and computational
thinking.
• Provided mentorship and support to students, helping them build confidence in coding and technology.
• Adapted teaching methods to accommodate different learning styles and skill levels.
GDG Members - Member of App Development Team, University of Science
Sept 2023 – February 2025
• Developed and optimized mobile and web applications as part of the GDG App Development Team.
• Designed and improved UI/UX components to enhance application usability and user experience.
• Contributed to open-source projects and technical blog posts to educate the developer community.
• Collaborated with team members to participate in hackathons and coding competitions.
• Engaged in discussions and workshops on the latest Google technologies and frameworks.
SKILLS
Languages: C++, Python,JavaScript, ExpressJS, SQL.
Technologies & Libraries: Microsoft SQL Server, Github, Slack, Jira, PyTorch, Tensorflow, Scikit-learn, Pandas.
CERTIFICATION
Medical Image Processing Workshop
Masayuki Fukuzawa, Dr Eng. Faculty of Information and Human Sciences, Kyoto Institute of Technology
Participated in a workshop focusing on medical image processing techniques.
Certification Image