Thomas Chuang

Software Engineer

I build practical software products that combine AI and geospatial systems—with a focus on clean architecture, performance, and good UX.

Go Bears!

LinkedIn Email Resume GitHub Medium

Software Engineer 0.99

Map Enthusiast & Adventurer! 0.99

Scroll

Education

Selected coursework and academic programs

University of California, Berkeley

Concurrent Enrollment StudentComputer Science

Aug 2025 – May 2026

Berkeley, CA

Relevant: CS 61C (Machine Structures), CS 162 (Operating Systems), Data 100 (Data Science)
Planned: CS 164 (Compilers), CS 161 (Computer Security)

National Chengchi University

Dual Bachelor of Arts in Risk Management & Insurance and Land EconomicsMinor in Management Information Systems

Sep 2020 – Jun 2026

Taipei, Taiwan

GPA: 3.86/4.00 • CS Field GPA: 3.98/4.00
Relevant: Data Structures (A+), Algorithms (A+), DBMS (A+), Software Engineering (A+)

Peking University

Exchange Student

Feb 2024 – Jun 2024

Beijing, China

Relevant: Deep Learning Models and Applications, Data Visualization

Professional Experience

Engineering, product, and research

Ultralytics

Associate Software Engineer

Aug 2024 – Present

Remote

Built real-time collaboration with FastAPI WebSockets + Redis for concurrent multi-user editing (sub-100ms perceived latency).
Designed conflict-safe state updates using optimistic concurrency (ETags) to preserve integrity under race conditions.
Integrated Segment Anything Model (SAM) for auto-labeling, reducing manual annotation time by ~40% on vision datasets.
Orchestrated CI/CD workflows for the open-source repo (51.8k stars), improving release reliability for global users.

GitHub Platform YOLO11

Esri R&D Center

Product Engineer Intern

Apr 2024 – Aug 2024

Beijing, China

Improved ArcGIS Earth 3D interaction by profiling rendering bottlenecks and reducing frame drops.
Prototyped a GPT-4o geospatial assistant to automate SQL-style queries and map generation from natural language.
Strengthened product stability through regression testing and code review practices for enterprise releases.

ArcGIS Earth

Academia Sinica

Undergraduate Researcher

Jul 2023 – Dec 2024

Taipei, Taiwan

Researched automated feature extraction for historical maps by combining YOLOv5 with Segment Anything (SAM).
Built a full-stack vectorization & verification system (Flask, PostgreSQL, Docker, OpenLayers).

History Map Project

Projects

Selected work — research-driven, visual, and interactive.

Historical Map of Taiwan Based on GeoAI

YOLOv5 + SAM (2023) · YOLOv8 Instance Segmentation (2024)

GeoAI pipeline for Taiwan historical map digitalization: started with YOLOv5-based feature recognition integrated with Segment Anything for faster digitization, then upgraded to YOLOv8 instance segmentation for improved vectorization quality.

Labeled 8 land-use classes and synthesized training data via random crop-composition to improve generalization.
Upgraded from object detection to instance segmentation, improving the quality of map feature extraction.
Result visualizations include detection, labeling, and prediction comparisons; packaged as a PDF report.

Paper (PDF)

Detection

Label

Prediction

System interface

Result (1)

Result (2)

Pmap — The Map for Precipitation 🌦️

Crowdsourced Reports + CWA Data · Subscription & Notifications · Cloud-Native

Pmap combines crowdsourced rain reports with official CWA weather data to estimate real-time precipitation more accurately. Users can report rain conditions (with photos), subscribe to fixed locations or regions, and receive in-app + email notifications based on schedules, new reports, or rainfall thresholds.

Fusion of public rain reports + CWA data to compute more accurate precipitation conditions.
Rain reporting flow with photos + real-time map experience (Leaflet) and dark mode.
Subscription & notification system: region-based new reports, scheduled rain updates, and threshold-based alerts (in-app + email).

GitHub Repo

Pmap demo: reporting, map interaction, subscriptions, notifications

System architecture (frontend / backend / notification / cloud)

CI pipeline (GitHub Actions + Docker build/test)

CD pipeline (deployment workflow / Portainer)

Real-time precipitation map (CWA + public reports)

Subscribe to fixed locations / regions

Configure schedules & thresholds

In-app notifications + email alerts

Taiwan Public Bicycle System Analysis

Time Series + Interactive Mapping (2021) · Spatio-temporal Insights (2024)

Built a data pipeline to track YouBike station dynamics over time: periodic scraping of open data, pandas time-series storage, matplotlib visualizations embedded into Folium popups, and later spatio-temporal analysis (DBSCAN, MRT transfer patterns) with Random Forest factor study.

Automated scraping + longitudinal station dataset (pandas) for trend analysis over time.
Interactive Folium map with per-station matplotlib time-series popups for exploration.
2024 analysis: DBSCAN station development, last-mile + MRT transfer issues, Random Forest feature impact; recognized in National Storymaps Competition.

GitHub (YouBikeAnalysis)StoryMaps (2024)Demo Website

Space-time cube for spatio-temporal dynamics

MRT transfer / bike relationship analysis

Last-mile & MRT transfer relationship insights

Riding route visualization (OD patterns)

Random Forest feature set (1)

Random Forest feature set (2)

Flow visualization of YouBike data

Folium popup embedding matplotlib time series

Heat map of station activity / demand patterns

Taiwan Convenience Store Analysis

Spatial Pattern (2021) · Spatio-temporal Prediction (2023)

Two-part study of convenience store competition in Taipei: (1) Average Nearest Neighbor (ANN) to test Hotelling-style spatial competition across five chains; (2) spatio-temporal prediction pipeline (Suitability → Space-Time Cube → MGWR) with statistical validation.

ANN-based spatial pattern analysis for five major convenience store chains (Taipei metro).
Spatio-temporal prediction built with suitability analysis, space-time cube, and MGWR; validated statistically.
Recognized in the National Storymaps Competition; detailed Medium write-up linked.