I am an AI Engineer Intern and Undergraduate AI Research Assistant at HCMUT (AITechLab - ML4U), deeply passionate about building scalable, production-grade intelligent systems. My technical focus lies at the intersection of Agentic AI, Speech Recognition (ASR), Real-Time Voice Agents, and LLM/SLM Inference optimization, backed by a solid foundation in Applied Machine Learning and Cloud infrastructure.
My primary goal is designing enterprise-ready agentic workflows, advanced RAG architectures, and robust tool/function-calling pipelines. Alongside engineering, my research investigates speech model mechanisms, benchmarking low-latency TTS/STT systems, and optimizing on-device inference for Small Language Models (SLMs). Across both research and implementation, I thrive on optimizing token economy, minimizing latency, and maximizing task accuracy to translate cutting-edge model capabilities into real-world impact.
I am constantly exploring emerging paradigms in AI and software architecture, and I am always open to connecting with forward-thinking engineers, researchers, and tech leaders who are shaping the next generation of intelligent technology.
|
|
|
|
|
|
| Domain | Technologies |
|---|---|
| Agentic AI & RAG |      |
| Machine Learning |       |
| Backend & Databases |       |
| Tools & Infrastructure |     |