Fisher Kuan

Agentic Engineering Lead

AI Architect & Engineer · MbarQ

I lead MbarQ's agentic engineering practice — the standards, tooling, and enablement for humans and AI agents to ship software together. Behind it: 10+ years of engineering, 7 shipping production AI for Fortune 500 and public-sector clients, and a pattern of re-tooling ahead of the curve — semiconductor R&D → ML → MLOps → GenAI → agentic systems.

10+ Years engineering
7 Years production AI
6 Industries shipped
mail@fisherkuan.com linkedin.com/in/fisherkuan github.com/fisherkuan
Scroll to see more

Core Skills

Agentic Engineering

Claude Code, GitHub Copilot, multi-agent orchestration, skill & context engineering, MCP integrations, agent sandboxing & guardrails, agent-maintained knowledge systems

Evaluation & Reliability

Evaluation harnesses, LLM-as-judge patterns, prompt & agent regression testing, monitoring and observability

GenAI / LLMs

RAG, agentic workflows, prompt engineering, Azure AI Foundry, chatbots, IDP/DocAI patterns

ML & MLOps

Supervised learning, NLP, time series, reinforcement learning, MLflow, model lifecycle management, CI/CD, reproducible pipelines

Cloud & Data

Azure (Databricks, Azure ML, AI Search), AWS, GCP, BigQuery, SQL/graph/vector databases, event-driven architectures

Languages / Frameworks

Python, PySpark, FastAPI, Docker, Git, Airflow/Prefect

Experience

MbarQ (Belgium)

Apr 2025 – Present

Agentic Engineering Lead

May 2026 – Present
  • Lead MbarQ's agentic engineering practice — setting the standards, tooling, and enablement for building with AI coding agents company-wide.
  • Defined the team's agentic way of working and drove company-wide adoption through internal workshops, reusable tooling, and industry research.
Agentic Engineering Knowledge Base & LLM-Wiki — Team-wide Claude Code standards, on-demand doctrine, and a library of reusable skills and playbooks, paired with an "LLM-Wiki" knowledge vault that agents maintain and that mirrors the internal repos. Tech: Claude Code, Markdown, Python, Git hooks / CI.
Claude Code Teams Bot — A Microsoft Teams bot that runs Claude Code autonomously: a queue-backed worker executes coding jobs on Azure and posts progress cards back into the chat, gated by an AAD sender allowlist and a secrets sandbox. Tech: TypeScript, Microsoft Teams SDK, Azure Container Apps, Bicep.
AI Translator Workflow App — A cross-platform desktop app that wraps Claude Code in headless mode to guide non-technical "AI Translators" through a structured, multi-stage project-scoping workflow, writing artifacts straight into the shared team vault. Tech: Python, FastAPI, React, pywebview, PyInstaller.

Senior AI Architect & Engineer

Apr 2025 – May 2026
  • Led end-to-end GenAI engagements: discovery, architecture, hands-on implementation, and go-live support.
LaunchPad (Internal) — Built a modular RAG accelerator framework on Azure for enterprise chatbot deployments; extended it with an agentic architecture to automate multi-step workflows. Tech: Python, FastAPI, Azure OpenAI, LangChain, Vue 3.
Fiducia 4.0 (Puratos) — Developed ML system predicting QC scores across multi-plant food production. Integrated raw material, process, and QC data sources into automated Azure ML pipelines. Enabled proactive quality control for Belgian and Mexican facilities.

Nemeon (Belgium)

Apr 2024 – Mar 2025

AI Solution Architect & Tech Lead

  • Designed and implemented GenAI solutions (document intelligence, process optimization) using LlamaIndex and LLM APIs.
  • Mentored engineers in applied GenAI patterns, delivery practices, and client communication.
BioSignature 2.0 (Johnson & Johnson) — Led consolidation of multiple microservices developed by different teams into an efficient, streamlined, modular data and ML pipeline utilizing event-driven architecture and AWS Step Function. Reduced prediction turnaround from days to hours. Tech: Python, AWS (Step Function, SageMaker), KServe, Argo, Kubernetes, Jenkins.

Dataroots (Belgium)

Jan 2022 – Nov 2023

Senior ML & MLOps Engineer, Coach

  • Coached junior ML engineers and interns across the full lifecycle with emphasis on engineering quality.
Dynamic Pricing (Proximus) — Built reinforcement-learning-based dynamic pricing system that drove 100% profit growth within nine months. Tech: Python, PyTorch.
Chatbot (BNP Paribas Fortis) — Developed a secure on-premises chatbot service with Llama 2.

Arinti (Belgium)

Nov 2020 – Dec 2021

AI Engineer

  • Streamlined pipelines with Azure Data Factory/Synapse and Azure DevOps.
Demand Forecasting (Unilever) — Developed sale and demand forecasting applications to reduce shortages and overproduction, shaping production strategies across facilities. Tech: Databricks, PySpark, Azure (Synapse, Cognitive Services).

Crunch Analytics (Belgium)

Nov 2019 – Nov 2020

Data Scientist

  • Built NLP feature extraction pipelines with BigQuery to support strategic product decisions.
  • Delivered NLP, web scraping, and optimization projects end-to-end.

TSMC (Taiwan)

Jan 2015 – Aug 2018

R&D Engineer

  • Developed ML models for semiconductor packaging optimization; reduced product development timelines by 20%.
  • Led thermal/structural analysis workstreams influencing reliability and design decisions.

Side Projects

Event Attendance App

Node.js • Express • Google Calendar API • PWA

Event RSVP platform with real-time attendance tracking, Google Calendar integration, mobile-first responsive design, and offline PWA support.

ChocoMold

React 19 • Three.js • React Three Fiber • Vite

Interactive web app transforming SVG artwork into 3D-printable chocolate mold STL files. Features drag-and-drop upload, real-time 3D preview, and one-click export.

Certifications

Education

MSc, Artificial Intelligence

KU Leuven

2018 – 2019

MSc, Materials Science & Engineering

National Chiao Tung University

2012 – 2014

BSc, Nano Science & Engineering

National Chiao Tung University

2008 – 2012