Jerel Ong
hamburger menu close

Welcome

This website is my technical portolio, where I showcase my projects and skills.

Projects

About Me

I graduated from SUTD (Singapore University of Technology and Design) with a degree in Computer Science and Design, and am a graduate of the AI Singapore Apprenticeship Programme (AIAP) Batch 20. I've got a strong interest in today's AI technologies, which led me to take up AI-focused courses and build real-world AI applications and solutions.

I'm also someone who's open to new and unfamiliar environments, and I'm always looking for ways to grow and keep improving in any way, not only in tech.

My Skills

HTML
CSS
JavaScript
React
Docker
GIT
Postman
Python
Java
TypeScript
Flask
Django
FastAPI
MongoDB
Node.js
PostgreSQL
TensorFlow
PyTorch
HugginFace

Projects

PowerPoint Slides Compliance Report Generation with AI

PowerPoint Slides Compliance Report Generation with AI

Developed an AI-driven application that automates the end-to-end generation of compliance report PowerPoint slides from custom data inputs. The solution applies robust software engineering practices and large language models (LLMs) to analyze user-provided data and transform it into structured, client-compliant presentations. In addition, a human-in-the-loop (HITL) workflow was implemented, enabling compliance managers to refine and edit the generated PPTX through prompt-based requests. By replacing a fully manual reporting process, the application significantly improves productivity, reducing report creation time and operational overhead.

More Details
Video Captioning in Military Scenarios

Video Captioning in Military Scenarios

Our team was tasked to develop a video captioning system that can generate captions for military scenarios. The system should be able generate detailed captions that describe the actions and events taking place in the video. The system should also be able to generate captions that are relevant to the military context, such as identifying specific objects, actions, and events that are relevant to military operations. We were also tasked to ensure that the system is able to generate captions in real-time, so that it can be used in live military operations. We named our final model DeepSub, a fine-tuned vision transformer model with InternVL2 as the base open source model. With our evaluation, our new model has achieved about 4x improvement in military object specificity when generating captions.

More Details
Streamlining Religious Diversity Training with an AI Webapp

Streamlining Religious Diversity Training with an AI Webapp

Our team partnered with a client promoting interfaith, interracial, and intercultural education to support trainers facing burnout from answering repetitive, sensitive questions. We developed an AI-powered web app that combines a curated FAQ system with a real-time chatbot, designed to handle complex topics respectfully and in line with the client's values.

The platform supports session-based customization, letting trainers tailor content and control access. A human-in-the-loop feedback system allows flagged responses to be reviewed and reused for few-shot training, enabling continuous improvement of the chatbot over time.

More Details
AI-Powered Research Assistant

AI-Powered Research Assistant

Ask anything about the provided document(s) with specific references within the document(s). Webiste Links supported.

More Details
AI-Powered Documentation & Learning Assistant

AI-Powered Documentation & Learning Assistant

A custom-built AI chatbot interface designed to enhance the documentation and learning experience. This project integrates features such as folder management, search, colored-tag filtering, and a prompt library system to streamline user workflows.

More Details
Bitcoin Predictor

Bitcoin Predictor

Designed and implemented an LSTM-based deep learning model in PyTorch to predict the next-day closing price of Bitcoin. The model uses 10+ years of historical data with engineered time-based features like day of the week and month. Achieved a test MAPE of ~2.48% and RMSE of ~$2519.98, demonstrating solid short-term forecasting capability for financial time series.

More Details