Experience
KMUTT Research Intern at IC2
May 2025 – PresentResearch intern at IC2, KMUTT under the supervision of Assoc. Prof. Dr. Jonathan Hoyin Chan. Developed a music diffusion model using PyTorch for high-quality audio generation and implemented baseline and Temporal Fusion Transformer models for end-to-end automated trading, achieving above-market returns with low risk.
EchoEye (echoeye.ca) – Chief Technology Officer (CTO)
Nov 2024 – PresentCo-founded and led a hardware-focused startup developing smart vision systems, winning the Rotman “LYBI” Competition against 100+ teams. Designed embedded systems for camera-based solutions, working with camera chipsets, SoCs, and low-latency networking protocols. Led full-stack web development using AWS, React, and Django. Managed and mentored a team of 4+ interns, coordinating across marketing and legal for patent filings and product marketing.
University of Toronto Machine Intelligence Student Team (UTMIST)
2023 - PresentLed academic paper-reading sessions on LSTMs, Encoder-Decoder models, and Transformers. Developed an LSTM Encoder-Decoder model for Neural Machine Translation using TensorFlow. Contributed to Strata, a collaborative research and engineering initiative within UTMIST.
University of Toronto Aerospace Team - Control Systems
2024 - PresentDeveloped MATLAB and Python-based control systems for the FINCH satellite mission, contributing to precise altitude planning and orientation control in space systems.
Yannes Solution Ltd.
Summer 2024Developed a Python-based system for organizing and processing on-site images, optimizing project documentation. Administered the installation of over 500 CCTV cameras across the Hong Kong Metro's East Rail Line.
Projects
Built a karaoke web app with real-time music separation using OpenAI Whisper and Demucs, FastAPI backend, and WebSocket communication.
A revolutionary approach to social competence therapy for children with Autism Spectrum Disorder, combining creativity, technology, and LEGO. Winner of Best AI for Creativity & Generative Arts at GenAI Genesis 2025.
Implemented a multiplayer “Try Not to Laugh” game using Three.js frontend, WebSocket communication, and data optimization for real-time interactions.
Designed an AWS-based algorithm to analyze roommate descriptions and compute compatibility through semantic embeddings, efficiently matching roommates with similar habits.
KMUTT Quant Finance Trading Model
Implemented baseline and Temporal Fusion Transformer models for end-to-end automated trading, achieving above-market returns with low risk.
SkySense – Predictive Aircraft Maintenance
Developed predictive maintenance solutions for aircraft using PyTorch, computer vision, and signal processing within UTMIST.