About
AI Application Development
I'm Yuanhao Feng, currently pursuing a Master of Information Technology, specialising in artificial intelligence, at the University of Melbourne. I studied software engineering as an undergraduate.
A central engineering challenge in AI applications is making probabilistic models work reliably in real business settings. Evaluation needs to cover business requirements and edge cases; architecture needs to define the responsibilities of model inference and deterministic logic; and the running system needs to balance output quality, performance, and cost. My work extends from agent orchestration and retrieval-augmented generation to backend APIs, data processing, deployment, and operations, spanning technical design, implementation, and production use.
Outside my studies, I explore projects in a range of areas, including AI applications, practical tools, and games. Many ideas start with an everyday need of my own. As a project develops, I pay more attention to how others will use it: whether getting started is straightforward, whether errors are clearly explained, and whether the software will be easy to maintain. One of the things I enjoy most is refining a personal tool into something other people want to use too.
I also built and maintain this website, from server configuration to page development. You can find a selection of my work on the Projects page.
Internships
AI Application Developer, Intern
COSCO Shipping Technology · Shanghai
Dec 2025 – Feb 2026
Led the container-number recognition technology evaluation, benchmarking six vision-language models and driving the team's shift from traditional OCR to a multimodal approach, raising the success rate from 37.5% to 98.3%. Also built a structured field-extraction agent for shipping emails with an automated evaluation pipeline, achieving 98.8% field-level accuracy.
Software Developer, Intern
COSCO Shipping Technology · Shanghai
Nov 2024 – Jan 2025
Independently developed a bill-of-lading PDF extraction pipeline end-to-end, designing a two-stage architecture that pairs OCR for spatial detection with an LLM for semantic understanding, and shipped it as a REST API. Also designed a geometric correction scheme for scanned documents that handles orientation detection and coordinate transformation in a single OCR pass, eliminating the overhead of a second recognition run.
Education
The University of Melbourne
Master of Information Technology · Artificial Intelligence
Feb 2025 – Dec 2026
Nanjing University of Information Science & Technology
B.Eng. in Software Engineering
Sep 2020 – Jun 2024