Email: hieunguyen1053@outlook.com
LinkedIn: https://www.linkedin.com/in/hieunguyen1053
Huggingface: https://huggingface.co/hieunguyen1053
I’m an AI Engineer with 2 years of experience in Natural Language Processing. With my knowledge of NLP, I enjoy applying AI to life and creating the best experience for users. I also spend time reading Science papers, learning new technologies and best practices to become a better engineer.
Programming Languages: Python, Java, C++
Frameworks/Libraries:
- Pytorch, Tensorflow
- Transformers, Optimum
- Onnxruntime, TensorRT
Fields of research:
- Machine Learning
- Natural Language Processing
- Computer Vision
Project: Ademax OCR (5 members, 1 front-end, 3 back-end, 1 ML)
- Description: A service used by a company to encode scanned documents into structured text documents, supporting metadata extraction.
- Technologies:
- Front-end: VueJS
- Back-end: Django, Redis, PostgresSQL, ElasticSearch
- Machine learning: Pytorch, Transformers, Accelerate, Optimum
- Responsibilities
- Generate training data, train models running on multiple GPUs (4 x Nvidia V100), evaluate and compare with previous models.
- Model optimization, model quantization, so that the model runs on CPU or GPU faster.
- Write API to execute multiple tasks concurrently, and handle queues to avoid overloading.
Project: Ademax Spelling (5 members, 1 front-end, 3 back-end, 1 ML)
- Description: Service used to check the spelling of Vietnamese text. This service is also integrated into the Office Word Add-in, serving a wide range of customers such as businesses, students, and ordinary users.
- Technologies:
- Front-end: VueJS, AngularJS
- Back-end: Django, Redis, PostgresSQL, ElasticSearch
- Machine learning: Pytorch, Transformers, Accelerate, Optimum
- Responsibilities
- Generate training data, train models running on multiple GPUs (8 x Nvidia A100), evaluate and compare with previous models.
- Model optimization, model quantization, so that the model runs on CPU or GPU faster.
- Write API to spell check Vietnamese text, classify many typos and suggest corrections. Supports executing multiple concurrent tasks and processing queues to avoid overloading.
- Studying Computer Science
- GPA: 8.2
- Member of the ICON Acedemic Club (@iconclub)