About

About¶

Hi, I'm Wayne 👋 — a GPU performance engineer, happiest when an upstream kernel fix lands. Currently, I'm a Field Application Engineer at Taiwan AI Labs, deploying on-premises LLM systems (FedGPT) into customer environments — Linux/Kubernetes operations, GPU serving, and customer-facing troubleshooting.

Previously, I was the sole developer of an enterprise multi-agent AI platform at SYNCROBOTIC, built internal coding agents at Advantech, and served at TSMC under the national R&D program. I hold an M.S. in Computer Science from NTUST (GPA 4.09), where I researched LLM safety alignment and privacy-preserving ML in Prof. Shao-Jui Wang's lab.

Outside work I live in the upstream LLM-inference stack — 17 merged/landed patches · 60 in review across FlashInfer, vLLM, SGLang, PyTorch, Dynamo, NVIDIA CUTLASS / TensorRT-LLM, and LMDeploy — see the auto-updating PR wall and Patches.

🛠️ Focus¶

Broadly, I care about inference performance you can trust — fast kernels that also compute the right answer. Three threads:

Serving internals: KV-cache, quantization trade-offs, attention kernels — enough depth to reason about cost and latency at design time.
Upstream enablement: early consumer-Blackwell (SM120) and NVFP4 support across kernels → engines → disaggregated serving; my favorite prey is the silent-correctness bug — tests green, answers wrong.
Trustworthy ML: safety alignment against harmful fine-tuning; federated learning, differential privacy, secure multi-party computation.

🗞️ News¶

Jul 2026: 💼 Joined Taiwan AI Labs as a Field Application Engineer — on-prem LLM deployments (FedGPT).
Jul 2026: 🧱 The live PR wall went up — every upstream patch, auto-updating.
Jul 2026: 📈 Upstream tally: 17 merged/landed · 60 in review across the LLM-inference stack.
Apr 2026: 🎓 M.S. in Computer Science from NTUST, GPA 4.09.
Jan 2026: 📝 SelGrad (first-author) submitted — under review at IEEE TDSC.
Sep 2025: 💼 Joined SYNCROBOTIC — sole developer of an enterprise multi-agent platform, shipped at two customers.
Jun 2025: 💼 Summer at Advantech building internal coding agents.
Dec 2024: 📜 NVIDIA DLI certificates — Accelerated Computing with CUDA (Python & C/C++).
Aug 2024: 🔬 Started graduate research on LLM security & privacy-preserving ML at NTUST.

📄 Selected Work¶

SM120 / NVFP4 enablement across the LLM-inference stack

FlashInfer · CUTLASS · vLLM · SGLang · TensorRT-LLM · Dynamo — kernels to engines to disaggregated serving

CUDABlackwellNVFP4

Live PR wall — prs.wayne.is-a.dev

Auto-updating feed of every upstream contribution, with RSS

Open Source17 merged60 in review

PR wall preview

SelGrad: Selective Gradient Projection for Efficient Safety Alignment Against Harmful Fine-Tuning

Wei-Cheng Chiu, et al. — under review at IEEE TDSC

SafetyAlignment

Enterprise multi-agent AI platform

PoC → production at two enterprise customers — routing layer, planning/execution/validation orchestration, hybrid RAG

AgentsRAGvLLM

📌 Misc¶

I'm from Taiwan and based in Taipei. Away from a profiler you'll find me tending an over-engineered Obsidian vault. The views on this site are my own and do not represent those of my employer or affiliated institutions.