Aspiring AI/ML Intern with Practical Pipeline Skills

Duc Anh Pham

Address Hanoi Phone +84-971****** Email **********.******@*****.***

** ******

• Aspiring AI, ML, DL, and Data Science intern with a solid academic foundation in machine learning, data processing, and statistical analysis. Passionate about transforming raw data into actionable insights and intelligent systems. Eager to apply practical skills in model building, data pipelines, and algorithm development to real-world challenges. 02 EDUCATION

Bachelor of Science in Mathematics and Informatics. Hanoi University of Science and Technology, Hanoi. Sept 2022 – Present

03 EXPERIENCE

• AI Engineer Intern

HBLAB JSC July – Sept 2025

- Researched and implemented a 2-stage License Plate Recognition (LPR) pipeline using YOLOv8 for detection and CRNN for character recognition.

-Preprocessed and annotated a dataset of over 3,000 images; applied data augmentation techniques (using Albumentations) to handle real-world challenges like glare, motion blur, and low-light conditions.

- Evaluated model performance, achieving an accuracy of 92% on the test set, and documented technical findings to support the R&D team in future optimization. 04 SKILLS

• Programming Languages: Python, C/C++, SQL

• Machine Learning: Pytorch, Keras, TensorFlow, Scikit-learn, XGBoost, LightGBM.

• Data visualization: Pandas, Matplotlib, Seaborn, PowerBI.

• Database: SQLite

05 PROJECT

Massive open online course

• CS50: Computer Science Courses and Programs from Harvard. Oct 2023

• Coursera: Programming Python for Everybody. May 2024

• Coursera: The Deep Learning Specialization. Sept 2024

• Coursera: IBM Data Science Feb 2025

Project

• HealthScan RAG Chatbot (Mobile App)

- Developed RAG chatbot for ingredient/health Q&A using embeddings + vector database retrieval + LLM response synthesis.

- Integrated chatbot into mobile app backend API, with profile-aware prompting

(allergies/conditions) and caching.

Tech: React Native (Expo), Python backend, LLM API, Embeddings, FAISS/Vector DB. Top 8 TechXpo Challenge 2025

• Voice Appointment Assistant & RAG Chatbot-Application Supporting Public Services

(Data For Life 2024)

- Built a voice pipeline: STT (Whisper/Cloud Speech) LLM NLU (intent + entities) Scheduling REST API TTS.

- Implemented RAG with embeddings + vector search to answer administrative procedure FAQs from internal docs.

Tech: Python, FastAPI/Flask, LLM API, STT, TTS, Embeddings, FAISS/Vector DB. Achievement: Advanced to the Conquest Round of Data For Life Season 3

• Linear Regression Model – Application with the SuperStore Dataset

- Researched linear regression models and machine learning models such as XGBoost, Random Forest, and KNN.

- Trained and evaluated the models on the given dataset.

- Applied the models to forecast profit and revenue.

- Enhanced model performance within the dataset.

Contact this candidate