Skip to content
View JovanYap's full-sized avatar

Block or report JovanYap

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
JovanYap/README.md

Hi there! 👋

Hey there! I am Jovan, a CS junior from the University of Michigan Ann Arbor, and my interests includes NLP/ML and SWE. I have trained and implemented a variety of Deep Learning models/LLMs for a wide range of applciations from medtech to chatbot technology. Currently, I am diving more into RLHF on open-source LLMs and App & Web development using Swift and React.

Experiences and Achievements

  • AI Software Engineer at GovTech (2024)
  • Computer Vision Engineer at University of Michigan Autonomous Robotics Club (2024)
  • NLP Engineer & Data Scientist at Land Transport Authority (2023)
  • Machine Learning Engineer at Medios (2022-2023)
  • SWE at UMich-SJTU (2022)
  • Intel ISEF'19 3rd Award

Technologies & Tools

JavaScript HTML/CSS/Bootstrap REST API ReactJS/VueJS Huggingface AWS/AzureML Pytorch SQL C/C++

Currently Working On...

  • Video Analytics
  • Peronal portfolio website
  • Open source projects
  • Apple app
  • Finetuning an opensource LLM with RLHF to create a chatbot:
  • Many other projects

Pinned Loading

  1. acestudios acestudios Public

    Breakout and RPG games developed using elm, Javascript and HTML/CSS

    HTML

  2. unet-tumor unet-tumor Public

    Brain Tumor Segmentation using 3D U-Net on MRI

    Jupyter Notebook

  3. TongZhengHong/NUSTimeTable TongZhengHong/NUSTimeTable Public

    TypeScript

  4. fullstack-distributed-systems fullstack-distributed-systems Public

    Fullstack Instagram-like platform, MapReduce distributed system and advanced search engine

  5. Breakout-DeepRL Breakout-DeepRL Public

    Deep RL agent trained to play the atari breakout game with tensorflow and computer vision

    Jupyter Notebook 1