Quan Nguyen

Func fact: I love HeyTea and Chicha San Chen

About Me

Hi, I’m Quan Nguyen, a Machine Learning Engineer (MLE) based in the San Francisco Bay Area. My work focuses on the intersection of Recommendation Systems (RecSys) and Large Language Model (LLM).

Starting in May 2026, I will be joining Google as a Software Engineer on the YouTube Recommendations team, where I’ll be working on ranking and recommendation systems to enhance user experience for millions.

My Professional Journey

My expertise lies in building scalable machine learning pipelines and optimizing distributed systems.

At Venera AI, I focused on LLM Post-Training and inference, engineering high-throughput pipelines for Qwen models using vLLM and Ray.

During my time at Adobe, I worked as an AI Agent Intern, optimizing Whisper inference and reducing agentic hallucinations through long-context management with LangGraph.

I also have a deep background in Recommendation Systems from my time at VCCorp, where I designed end-to-end ML pipelines and distributed Graph Neural Network (GNN) training to serve personalized content to millions of daily users.

Education

I hold a Master of Science in Computer Science from the University of Maryland, College Park (UMD) and a Bachelor of Science from Gettysburg College.

news

May 27, 2025	I start my internship at Adobe!

latest posts

Mar 08, 2026	Brief of AI/ML coding interview questions (Leetcode style)
Mar 08, 2026	Brief of CUDA/GPU coding interview questions (Leetcode style)
Mar 08, 2026	Brief of Data-Structure & Algorithm (DSA) coding interview questions

selected publications

AAAI
Predicting Perceived Music Emotions with Respect to Instrument Combinations

Viet Dung Nguyen, Quan H. Nguyen, and Richard G. Freedman

Proceedings of the AAAI Conference on Artificial Intelligence, Jul 2024

Abs DOI Bib

Music Emotion Recognition has attracted a lot of academic research work in recent years because it has a wide range of applications, including song recommendation and music visualization. As music is a way for humans to express emotion, there is a need for a machine to automatically infer the perceived emotion of pieces of music. In this paper, we compare the accuracy difference between music emotion recognition models given music pieces as a whole versus music pieces separated by instruments. To compare the models’ emotion predictions, which are distributions over valence and arousal values, we provide a metric that compares two distribution curves. Using this metric, we provide empirical evidence that training Random Forest and Convolution Recurrent Neural Network with mixed instrumental music data conveys a better understanding of emotion than training the same models with music that are separated into each instrumental source.
@article{Nguyen_Nguyen_Freedman_2024, title = {Predicting Perceived Music Emotions with Respect to Instrument Combinations}, volume = {37}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/26910}, doi = {10.1609/aaai.v37i13.26910}, number = {13}, journal = {Proceedings of the AAAI Conference on Artificial Intelligence}, author = {Nguyen, Viet Dung and Nguyen, Quan H. and Freedman, Richard G.}, year = {2024}, month = jul, pages = {16078-16086}, }