01

About Me

AI engineer and photographer based in Taipei, Taiwan.

I'm a Computer Science graduate from National Taiwan Ocean University (Class of 2026). My most recent project, RiffNode — an AI guitar effects studio built entirely with native Apple frameworks — won the Apple WWDC26 Swift Student Challenge.

At ITRI I trained and deployed multi-task driving-perception models down to a Jetson Nano, and my capstone team built a deep-learning volleyball analytics platform. Lately I have been auditing whether guitar-tone models quietly change a player's touch, and building a macOS app whose architecture the compiler enforces. I like working across the stack — on-device ML, audio DSP, systems Swift — and turning hard problems into things people can actually use.

YuJia Liang

Technical Skills

Languages

PythonTypeScriptRustSwiftC++DartSQL

ML / AI

PyTorchTensorFlowOpenCVYOLOONNXTensorRTROSJetson Nanoscikit-learnRAG

Apple Platforms

SwiftUIAVFoundationAccelerate/vDSPScreenCaptureKitCore ImageFoundation Models

Frontend & Mobile

ReactNext.jsTailwindFlutter

Backend & Infra

FastAPIPostgreSQLMongoDBRedisFirebaseDockerGCP

DevOps & Testing

GitGitHub ActionspytestSwiftPM

Daily Tools

ClaudeChatGPTCursorGitHub CopilotGeminiFigma

Experience

AI Image Recognition Intern

ITRI (Industrial Technology Research Institute)

Electronics and Optoelectronics Research Laboratories

Hsinchu, TaiwanJun. 2025 – Aug. 2025
  • ·Trained YOLOPX, a multi-task panoptic driving perception network doing object detection, drivable-area segmentation and lane segmentation in a single forward pass — reaching 0.972 mIoU (drivable area), 0.793 mIoU (lane) and 0.838 [email protected] over 4 classes after 200 epochs on ITRI's in-house driving dataset
  • ·Extended the open-source YOLOPX codebase by ~1,900 lines (6 files rewritten, 5 added) for ITRI's data format, building a YOLO-segmentation loader and a Mosaic/MixUp/Albumentations augmentation pipeline to replace one that handled BDD100K only
  • ·Owned the edge deployment path: network pruning, ONNX export, a tool resolving dynamic convolution-bias subgraphs that blocked TensorRT conversion, a TensorRT/PyCUDA engine for NVIDIA Jetson Nano, and image + detection streaming to a desktop PC over Ethernet/ROS at 30 FPS with sub-50ms latency
  • ·Delivered a command-line batch-inference tool for ARTC (Automotive Research & Testing Center) running the trained model across image and video datasets including a new rainy-weather set; separately reproduced and benchmarked YOLOP, YOLOPv2, YOLOPX and A-YOLOM to identify deployment-viable designs

Education

National Taiwan Ocean University logo

National Taiwan Ocean University

B.S. in Computer Science and Engineering

Keelung, Taiwan2022 – 2026
Cotter High School logo

Cotter High School

High School Diploma

Winona, MN, USA2019 – 2021

Languages

MandarinNative
EnglishFluentTOEFL 110 · TOEIC 920
JapaneseIntermediateJLPT N3

Beyond Code

Off the clock I captain my department's volleyball team, scuba dive, play guitar, and develop film as darkroom officer of NTU's photography club. Most of it ends up in front of a camera sooner or later — the results live on the Photography page.

Resume

YuJia_resume.pdf