Work Experience

Research Assistant, Agent Harness and Model Co-Optimization
Sep. 2026 - Present
Language Technologies Institute, Carnegie Mellon University · Pittsburgh, PA
NeuLab · advised by Prof. Graham Neubig and Lintang Sutawika
LLM Agents Evaluation Infrastructure Data Selection vLLM GPU Clusters
  • Owned the data-selection track of a joint harness-and-model optimization project, turning failed agent trajectories into the training-data signal for rejection-sampling fine-tuning (RSFT).
  • Built a failure-analysis pipeline over 720 agent trials of raw JSON telemetry, classifying each trial by exit state and exposing a 15.4% silent failure rate the reported mean absorbed, a 10-point AIME swing.
  • Selected evaluation subsets with nearest-neighbour search over a 1.79M-row dataset, re-embedding all 17,398 DAPO-Math problems with sentence-transformers to rule out a text artifact, 91 of 100 picks surviving.
  • Closed a silent cross-job failure on a shared multi-tenant GPU cluster, where a dead vLLM server sent every trial to another job's endpoint, with dynamic port allocation and served-model assertions shipped as a pull request.
Software Engineering Intern
Jun. 2025 - Mar. 2026
ASUS · Taipei, Taiwan
Open Cloud Infrastructure Software R&D Team
TypeScript End-to-End Testing MCP LLM Tooling VS Code Docusaurus
  • Cut a full regression pass from ~16 hours to ~1-2 hours with a TypeScript end-to-end (E2E) test suite covering ~95% of previously manual cases across Linux, Windows, and macOS.
  • Automated issue triage with a GitLab Model Context Protocol (MCP) agent, pairing an LLM classification prompt with MCP tool calls to auto-classify, label, and route issues.
  • Shipped four context providers into a VS Code AI coding assistant, adding commit-history, OS-metadata, current-file, and repository-map context selected from an evaluation of candidates.
  • Authored the assistant's Docusaurus documentation site, reducing hands-on onboarding support for adopting teams.
Startup Engineer
Jun. 2026 - Aug. 2026
RoomMuse · Pittsburgh, PA
Swift RealityKit AR Computational Geometry Classical CV
  • Caught unbuildable layouts at design time rather than on install day with a six-rule geometric conflict engine that blocks any unit sealing a socket, pipe, or doorway while passing intended connections (45 tests).
  • Localized wall sockets from an iOS AR room scan built in Swift with RealityKit using a classical-CV pipeline (adaptive thresholding, connected components, NMS), ray-casting detections through the camera pose onto scanned wall planes.
Research Assistant, Edge LLM Compression
Sep. 2025 - Feb. 2026
Wireless Ad-Hoc and Sensor Networks Laboratory, NCU · Taoyuan, Taiwan
Advised by Min-Te Sun
PyTorch GPTQ Knowledge Distillation DeepSpeed Edge Deployment
  • Scaled teacher-student distillation to data-parallel training on 3 GPUs with DeepSpeed ZeRO-2, sharding optimizer state and gradients, since ZeRO-3 parameter sharding corrupts GPTQ-packed weights.
  • Recovered 4-bit accuracy at 2-bit model size (IoU 0.9998, 1.18 GB) by fine-tuning a Llama-3.2 student with GPTQ quantization and LLM-Neo knowledge distillation in PyTorch.
  • Surveyed llama.cpp, vLLM, and SGLang for serving on a Jetson AGX Orin edge target, mapping latency versus throughput across PagedAttention, continuous batching, and prefix-cache reuse.
AI Technical Writer and Educator
Apr. 2025 - Dec. 2025
AI POST · Remote
Technical Writing AI Coding Workflows Developer Education Course Design
  • Authored the Vibe Coding column, translating AI coding workflows into hands-on tutorials that reached 50K+ readers and drove 42% platform content growth.
  • Designed and taught an AI-workflow course, plus the Her Path in Tech and Vibe Coding workshops, each reaching 200+ participants.
Frontend Engineer
Aug. 2024 - Jun. 2026
NCU College of Hakka Studies · Taoyuan, Taiwan
Frontend Web Performance Accessibility Security
  • Lifted mobile Core Web Vitals from 61% to 86% for 8,000+ monthly visitors, meeting WCAG 2.1 AA accessibility on a production site.
  • Remediated 17 security vulnerabilities across the codebase using automated review and scanning.

Selected Projects

Dual-Strategy UAV Path Planning
Sep. 2024 - Dec. 2025
First-author paper, Ubi-Media 2026 (Springer CCIS vol. 2940)
C++ Python Point Clouds Path Planning AirSim
  • Designed a dual-strategy planner trading layered MST-DFS for structured-space traversal against collision-aware A* replanning, cutting path-generation time over 5× and path length up to 14%.
  • Built the 3D point-cloud pipeline in C++ and Python, slicing raw .pcd scans into layers and chaining per-layer KNN and MST into a DFS traversal, with normal-vector correction for full coverage.
  • Validated 100% collision-free operation in AirSim against a random-order baseline on real-world building models.
Museum Artifact Recognition App
May 2024 - Nov. 2024
Swift TensorFlow Lite On-Device Inference iOS AWS EC2
  • Shipped on-device model inference in an iOS app, running the team's YOLOv8n and Pix2Pix reflection-removal models in Swift with TensorFlow Lite at 94.5% accuracy across 7 classes.
  • Integrated the iOS client with the team's AWS EC2 REST inference API, adding a cloud path for multi-user recognition.
Everything above is on one page, in ATS-friendly form, in my resume.
Download resume (PDF)