I build generative-AI and agentic systems and put them in production: multi-agent and RAG apps with LangChain / LangGraph, served as tested, containerized FastAPI services with CI/CD. Underneath sits real applied-ML and GPU depth (PyTorch, CUDA, NVIDIA PhysicsNeMo) from peer-reviewed research, which most LLM engineers don't have.
Multi-agent and RAG applications with LangChain / LangGraph and AutoGen. Tool routing, MCP, FAISS retrieval, and prompt engineering across OpenAI, Claude, Groq, Hugging Face, and Ollama, with the LLM wrapped around a deterministic, cited, tested core.
Systems that ship and survive: FastAPI services, Docker, GitHub Actions CI/CD, 525+ automated tests, PyPI packaging, model cards, and live demos. Built so anyone can reproduce the headline number themselves.
A real GPU and modeling foundation from peer-reviewed research: PyTorch, CUDA, NVIDIA PhysicsNeMo, neural operators, time-series forecasting, and uncertainty quantification. This is the depth behind the engineering.
GPU physics-informed neural operators for groundwater: one operator trained across all
61 wells, benchmarked head-to-head against the per-well gray-box ODEs. A real PhysicsNeMo
port with .mdlus checkpointing, a
CUDA GPU benchmark, leave-one-well-out generalization, and a probabilistic forecast model
with calibrated intervals. It also reports where it still trails the gray-box
baseline.
An open-source toolkit for water data, hydrology, and agricultural water management. 15 unified data sources (USGS, FAO, GEMStat, EU WFD and more), Bulletin 17C flood frequency, FAO-56 crop water, baseflow separation, and an agentic AI engine that scores 26 methodologies and auto-executes 7 pipelines. CAMELS-validated, 500+ tests, on PyPI.
A personal agronomy agent for aquaponics. Instead of retrieving what a paper said, Agronaut computes the answer for your specific system: a tool-calling LLM collects facts and routes, while a deterministic, fully tested engineering core does the math, now calibrated against an open real-pond dataset. It remembers your system across sessions and reasons over a curated troubleshooting knowledge base. Every result lists the coefficients it used (with sources) and what it does not model, so you always know the limits of the design.
claude > /paper-agent review manuscript.docx ✓ runtime Claude Code plugin v1.5.0 ✓ citations Semantic Scholar MCP ✓ guard anti-fabrication: 0 invented refs → manuscript.reviewed.docx
A Claude Code plugin that turns the agent into a disciplined manuscript
collaborator: five modes (draft, review, revise, proofread, audit), citations resolved
through the Semantic Scholar MCP (auto-wired on install), and hard
anti-fabrication guardrails with pause-and-confirm after every section. Calibrated for
hydrology and IEEE journals, with a generic profile for any quantitative-science field and a
clean .docx round-trip.
/plugin marketplace add Rekin226/paper-agent
/plugin install paper-agent@paper-agent
$ deploy fasobat --env azure ✓ stack Django · React · PostgreSQL · Azure ✓ modules sites · crews · materials · GIS ✓ status live · paying clients → construction-site management, shipped
A construction-site management platform I built and shipped through POUK YAM, my consultancy: scheduling, crews, materials, and GIS-based site tracking in one Django / React application on Azure REST services. I designed it, built it, deployed it, and I support real clients on it across water, energy, and agriculture.
I build production AI: generative and agentic systems, multi-agent and RAG apps served as tested, containerized services, on top of a real applied-ML and GPU foundation. What I bring that most LLM engineers don't is a scientist's discipline. I respect the constraints, validate out of sample, and never ship a number I cannot reproduce.
That discipline is earned, not claimed. During my Ph.D. at Feng Chia University I built physics-informed gray-box models of the Chou-Shui Chi alluvial fan in central Taiwan and predicted groundwater across 33 wells with RMSE between 0.07 and 0.24 m. HydroPhysicsAI later scaled that approach to a single neural operator across all 61 wells. That is the testing rigor I bring to every system I ship.
Today I am Applied AI Researcher and Developer at the Taiwan Polar Institute, where I build and open-source generative-AI and agentic systems with verifiable cores, served as tested software other people can actually run. I also founded POUK YAM, a consultancy in water, environment, energy, and agriculture, where I ship commercial software like FASOBAT.
Open to AI/LLM engineer, generative-AI / agentic-systems engineer, and applied-AI / ML engineering roles.
Ph.D., Infrastructure Planning & Engineering, Feng Chia University (2023).
Full academic background on LinkedIn (opens in new tab)4 peer-reviewed papers (3 SCIE-indexed, incl. Hydrogeology Journal 2026) and 1 granted patent (TW M661364).
Read on Google Scholar (opens in new tab)Open to AI/LLM engineering and applied-AI roles, collaborations, and consulting.