Skip to content
View ivankqw's full-sized avatar

Block or report ivankqw

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
ivankqw/README.md

πŸ‘‹ Hi, I'm Ivan Koh

Profile Views

I'm a Software Engineer focused on building transformative systems. My expertise spans ML, Data Engineering, and Software Development, with a passion for creating solutions that drive real-world impact.

πŸ”­ Currently at Openspace Ventures, architecting end-to-end AI solutions that revolutionize investment processes and accelerate portfolio company growth. Leading the development of scalable microservices and high-impact data science initiatives.

🌱 Actively contributing to open-source and always open to collaborating on innovative projects that push technological boundaries.

πŸ”₯ GitHub Stats

GitHub Streak

πŸ’» Tech Stack

Languages & Frameworks

My Skills

Web Development & MLOps

My Skills

Data & Cloud

My Skills

πŸš€ Featured Projects

  • Implementing attention mechanisms for improved caption generation
  • Experimenting with transfer learning using pre-trained vision models
  • Conducted architecture experiments comparing different encoder-decoder setups
  • Tech: PyTorch, Transformers, ResNet, BERT
  • Built RAG system for analyzing Singapore datasets using LangChain
  • Implemented custom function calling for data manipulation tasks
  • Created autonomous agent system for end-to-end analysis workflow
  • Leveraged vector stores for efficient context retrieval
  • Tech: LangChain, OpenAI, FAISS, Pandas
  • Experiments with traditional ML and neural networks
  • Tech: scikit-learn, TensorFlow, XGBoost
  • Developed automated data pipeline using Apache Airflow
  • Implemented ML experiment tracking with MLflow
  • Created CI/CD pipeline for model deployment
  • Built monitoring system for model performance
  • Tech: Airflow, MLflow, Docker, GCP
  • Developed full-stack web application for finance management
  • Implemented CRUD operations with responsive UI
  • Built RESTful API with authentication
  • Created interactive dashboards for expense analysis
  • Tech: React

🌐 Connect with Me

LinkedIn Portfolio Email

Pinned Loading

  1. image-captioning-project image-captioning-project Public

    deep learning image captioning project

    Jupyter Notebook

  2. sg-data-analyst sg-data-analyst Public

    LLMs as Data Analysts over Singapore Datasets πŸ€–

    Python 1

  3. bandytan/Fake-Twitter-Account-Detection bandytan/Fake-Twitter-Account-Detection Public

    Using traditional machine learning and neural networks, we built a model that can identify different types of fake Twitter users, such as fake followers and spammers.

    Jupyter Notebook 9 1

  4. bandytan/Kickstarter-Campaign-Success-Predictor bandytan/Kickstarter-Campaign-Success-Predictor Public

    A machine learning model that predicts the success of Kickstarter campaigns for backers to maximise their net return on investment.

    Jupyter Notebook 2 1

  5. housing-mlops housing-mlops Public

    Jupyter Notebook 1

  6. xghan99/csb-rn409 xghan99/csb-rn409 Public

    A one-stop finance app to track your investments, expenditure and income.

    JavaScript