Git Product home page Git Product logo

Nguyen Trong Hieu (@hieunguyen1053) - AI Engineer

Email: [email protected]

LinkedIn: https://www.linkedin.com/in/hieunguyen1053

Huggingface: https://huggingface.co/hieunguyen1053

Visitor GitHub followers

SUMMARY

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.

TECHNICAL SKILLS

Programming Languages: Python, Java, C++

Frameworks/Libraries:

  • Pytorch, Tensorflow
  • Transformers, Optimum
  • Onnxruntime, TensorRT

Fields of research:

  • Machine Learning
  • Natural Language Processing
  • Computer Vision

PROFESSIONAL EXPERIENCE

Ademax (Vietnam) - AI Engineer (2021 - Now)

Project: Ademax OCR (5 members, 1 front-end, 3 back-end, 1 ML)

LINK DEMO

VIDEO DEMO

  • 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)

VIDEO DEMO

  • 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.

EDUCATION

Ton Duc Thang University (Vietnam) 08/2018 - now

  • Studying Computer Science
  • GPA: 8.2
  • Member of the ICON Acedemic Club (@iconclub)

STATS

My wakatime stats

Most used languages

Hieu Nguyen's Projects

bertsearch icon bertsearch

Elasticsearch with BERT for advanced document search.

chat-ui icon chat-ui

Open source codebase powering the HuggingChat app

colossalai icon colossalai

Making big AI models cheaper, easier, and more scalable

cryptopp-example icon cryptopp-example

A few examples use the crypto ++ library for hash functions, block ciphers, public key signature schemes.

d2l-vn icon d2l-vn

Một cuốn sách tương tác về học sâu có mã nguồn, toán và thảo luận. Đề cập đến nhiều framework phổ biến (TensorFlow, Pytorch & MXNet) và được sử dụng tại 175 trường Đại học.

danes icon danes

DANeS is an open-source E-newspaper dataset by collaboration between DATASET JSC (dataset.vn) and AIV Group (aivgroup.vn)

dify icon dify

An Open-Source Assistants API and GPTs alternative. Dify.AI is an LLM application development platform. It integrates the concepts of Backend as a Service and LLMOps, covering the core tech stack required for building generative AI-native applications, including a built-in RAG engine.

dltk icon dltk

Deep Learning Toolkit for Medical Image Analysis

doctr icon doctr

docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.

easyspider icon easyspider

A visual no-code/code-free web crawler/spider一个可视化爬虫软件,可以无代码图形化设计和执行的爬虫任务

etnlp icon etnlp

ETNLP: A toolkit to evaluate, extract, and visualize multiple embeddings

evbcorpus icon evbcorpus

The English-Vietnamese Bilingual Corpus (EVBCorpus) is a collection of English and Vietnamese parallel translations and bitexts.

facenet_opencv_dnn icon facenet_opencv_dnn

This project will show you how to deploy a pretrain [tf faceNet model](https://github.com/davidsandberg/facenet) using the OpenCV-Dnn tools.

fairseq icon fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

fastbook icon fastbook

The fastai book, published as Jupyter Notebooks

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.