Kevin Tan, Cloud Solutions Architect

About Me

Singapore-based cloud architect and engineering leader with 18+ years building and shipping software, including 10+ years leading distributed teams across Singapore and China. I take emerging technology — Generative AI and agentic systems — from prototype to production at scale, with hands-on depth in resilient, distributed cloud-native systems. AWS Certified Generative AI Developer – Professional, author of 35+ technical articles, maintainer of three open-source AI/MCP packages (39K+ combined PyPI downloads), and named inventor on two granted patents.

Writes at blog.jztan.com — 35+ articles across cloud architecture, AI engineering, and distributed systems.

Experience

Deputy R&D Director

GDC Technology • Jan 2022 - Present

  • • Lead a distributed R&D organization across Singapore and China, growing engineers into technical-lead and management roles and building a culture of accountability.

  • • Own end-to-end delivery of multiple concurrent R&D initiatives from concept through prototype to production pilot, with agile execution and transparent stakeholder reporting.

  • • Established Generative AI and agentic initiatives — production pilots on Amazon Bedrock with RAG, the Strands Agents SDK, and MCP servers extending agents into enterprise data sources.

  • • Provide architectural leadership across product lines, reviewing designs for scalability, security, and extensibility.

  • • Partner with product, business, and executive stakeholders to translate technical trade-offs into clear business decisions and multi-year roadmaps.

Senior R&D Manager / R&D Manager

GDC Technology • Jan 2013 - Dec 2021

Titles held: Senior R&D Manager, R&D Manager, Deputy R&D Manager

  • • Directed architecture and development of a second-generation product platform across product, engineering, and go-to-market teams.

  • • Led cross-functional cloud and on-prem initiatives improving deployment efficiency and scalability.

  • • Established Git-Flow and Kanban practices, improving development cycle time and cross-functional collaboration.

  • • Built CI/CD pipelines (GitHub Actions) for automated testing, deployment, and rollback.

  • • Built trust with senior technical and C-level stakeholders through architecture reviews, influencing strategic technology decisions.

R&D Engineering Roles

GDC Technology • Jul 2007 - Dec 2012

Titles held: Senior R&D Engineer, R&D Engineer

  • • Designed and delivered first-generation Theatre Management System deployed across large cineplex environments.

  • • Developed electronic cinema playback systems with HDCP security compliance and high reliability requirements.

Software Engineer

Cyberlink • Jun 2006 - May 2007

  • • Developed multimedia software solutions in Python, C++, and DirectShow for global OEM partners including HP, Dell, and NEC.

Education

National Taiwan University

Bachelor of Science (BSc) Computer Science • Jun 2006

Certifications

AWS Certified Generative AI Developer - Professional
Issued May 2026
AWS Certified Solutions Architect - Associate
Issued April 2024

Technologies

Generative AI & Agentic Systems
Amazon Bedrock RAG Strands Agents SDK MCP Servers Agent Observability & Evaluation
Cloud & Infrastructure
AWS Serverless Lambda API Gateway DynamoDB S3 SQS EventBridge CloudFront X-Ray IaC (CloudFormation/Serverless) CI/CD (GitHub Actions)
Engineering Leadership
Distributed Teams Coaching to Tech-Lead Delivery Discipline
Programming
Python C/C++ Django PostgreSQL

Patents

System and method for providing failover of storage for digital cinema broadcasting
US 10,798,427 B2 · Issued: October 6, 2020
System and method for cinema play memory failover
CN 107743245 B · Issued: July 24, 2020

Portfolio

Three open-source AI/MCP packages with 39K+ combined PyPI downloads.

blueclaw

AI agent observability

Summary:

Open-source CLI for AI agent observability, context masking, regression testing, and HTTP API. v2.0+, with over 6,000 PyPI downloads.

Highlights:

  • • CLI tool for tracing and observing AI agent behaviour in production.

  • • Context masking for safe logging of sensitive data.

  • • Regression testing support and HTTP API for integration.

Tech Stack:

Python CLI Observability PyPI

pdf-mcp

MCP server

Summary:

MCP server that lets Claude Code and AI agents read PDFs beyond their token limits. 40+ GitHub stars and over 17,000 PyPI downloads.

Highlights:

  • • Solves Claude Code's large-PDF token limit with a lightweight MCP server.

  • • Built on FastMCP and published on PyPI; over 17,000 downloads to date.

  • • Used in production AI agent workflows.

Tech Stack:

Python MCP FastMCP PyPI

Redmine MCP Server

AI Integration & Developer Tools

Summary:

Production-ready Model Context Protocol server enabling AI assistants to interact with enterprise Redmine systems with strong security and operational guarantees.

Highlights:

  • • Built production-ready MCP server using FastMCP, enabling AI agents to manage enterprise project workflows programmatically.

  • • Implemented secure authentication supporting API keys and credential-based access with automatic session handling.

  • • Designed modular architecture with testing and Docker-based deployment for scalable production use.

  • • Implemented secure file handling with automatic expiry and cleanup for enterprise compliance.

  • • Published to PyPI with full documentation; over 16,000 downloads to date.

Tech Stack:

Python FastMCP MCP Docker Redmine API PyPI Security

Get in touch

I write and build in public about AI agents, MCP, and production cloud systems. I'm always happy to hear from fellow practitioners, and occasionally open to advisory conversations or speaking opportunities. Email is the best way to reach me.

Email → LinkedIn GitHub Medium Blog