Fisher Kuan

Agentic Engineering Lead · AI Architect & Engineer

mail@fisherkuan.com linkedin.com/in/fisherkuan github.com/fisherkuan fisherkuan.com (Full CV)

Summary

Agentic Engineering Lead with 10+ years of engineering, 7 shipping production AI for Fortune 500 and public-sector clients. Leads MbarQ's agentic engineering practice — standards, tooling, and enablement for building software with AI agents — on top of end-to-end GenAI/LLM architecture and MLOps delivery.

Skills

Agentic Engineering
Claude Code, multi-agent orchestration, skill & context engineering, MCP, sandboxing
Evaluation & Reliability
Eval harnesses, LLM-as-judge, prompt/agent regression testing, observability
GenAI / LLMs
RAG, prompt engineering, Azure AI Foundry, LangChain
MLOps
MLflow, CI/CD, model lifecycle, monitoring, reproducible pipelines
Cloud & Data
Azure (Databricks, Azure ML, AI Search), AWS, GCP, vector/SQL/graph DBs
Languages & Frameworks
Python, PySpark, FastAPI, Docker, Airflow/Prefect

Experience

MbarQ (Belgium)

Apr 2025 – Present

Agentic Engineering Lead

May 2026 – Present
  • Lead MbarQ's agentic engineering practice — standards, tooling, and enablement for building with AI coding agents company-wide.
  • Defined the LLM-Wiki way of working (agent-maintained team knowledge vault) and built its tooling: an autonomous Claude Code Teams bot on Azure and a desktop app for non-technical "AI Translators."

Senior AI Architect & Engineer

Apr 2025 – May 2026
  • Led end-to-end GenAI engagements: discovery, architecture, hands-on implementation, and go-live support.

LaunchPad — Modular RAG accelerator framework on Azure for enterprise chatbots, extended with an agentic architecture for multi-step workflows. Tech: Python, FastAPI, Azure OpenAI, LangChain, Vue 3.

Fiducia 4.0 (Puratos) — Predictive quality control: ML classifiers predicting run-level QC failures before lab results from process/sensor, raw-material lineage, and historical QC data; end-to-end Azure ML pipelines (per-product/per-criterion training, drift monitoring) across plants, with "golden recipe" analysis turning models into actionable process settings.

Nemeon (Belgium) — AI Solution Architect & Tech Lead

Apr 2024 – Mar 2025
  • 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 into a streamlined event-driven ML pipeline, reducing prediction turnaround from days to hours. Tech: Python, AWS (Step Functions, SageMaker), KServe, Argo, Kubernetes, Jenkins.

Dataroots (Belgium) — Senior ML & MLOps Engineer

Jan 2022 – Nov 2023
  • Coached junior ML engineers across the full lifecycle with emphasis on engineering quality.

Dynamic Pricing (Proximus) — Built RL-based dynamic pricing system driving 100% profit growth in nine months. Tech: Python, PyTorch.

Chatbot (BNP Paribas Fortis) — Developed a secure on-premises chatbot service using Llama 2.

Earlier Experience

2015 – 2021
  • Arinti (Belgium) · AI Engineer — Demand forecasting for Unilever on Databricks/PySpark/Azure ML, reducing shortages and overproduction across facilities. (2020–2021)
  • Crunch Analytics (Belgium) · Data Scientist — End-to-end NLP, web scraping, and optimization projects. (2019–2020)
  • TSMC (Taiwan) · R&D Engineer — ML models for semiconductor packaging optimization; cut product development timelines by 20%. (2015–2018)

Certifications

  • Azure AI Engineer Associate
  • Azure Data Scientist Associate
  • Databricks Associate Developer
  • TensorFlow Developer

Education

  • MSc, Artificial Intelligence
    KU Leuven — 2018–2019
  • MSc Materials Science · BSc Nano Science
    National Chiao Tung University — 2008–2014

Languages

English (Fluent)

Mandarin (Native)

Dutch (A2)