Frontend Engineer building AI-assisted tools for complex workflows.

Ten years of React and TypeScript across Bunny.net, Sportradar, and a professional trading platform — lately focused on MCP agent tooling and the interfaces that make AI workflows usable.

Selected outcomes · Bunny.net platform work

build time
page speed
components shipped
Frontend-focused AI-native developer · APAC-friendly remoteStack · TypeScript / React / NodeFocus · MCP, Agentic UX, DX

Selected work

A concise view of product interfaces, workflow tooling, and performance systems shaped across React and TypeScript stacks.

Bunny.net Platform & CMS

Owned the full development cycle as the solo developer and maintainer within Bunny.net's marketing team, shipping high-traffic Gatsby/React pages, offer flows, calculators, and CMS-backed components while stabilizing the platform and migrating a discontinued CMS.

Outcomes
  • Build time reduced from 15 to 4 minutes
  • Runtime performance improved by 45%
  • 100+ product and pricing components
Role
Senior Frontend Developer
Bunny.net landing page screenshot

Sportradar Betting UI

Shipped bet slip workflows for Sportradar's new betting platform after joining the early implementation phase, growing into frontend lead, leading a four-person frontend team, migrating first customers from legacy systems, coordinating with architects and stakeholders, and building internal tools.

Outcomes
  • React betting workflows for 100K+ users
  • Faster bet slip interactions after the legacy migration
Role
Senior Frontend Developer
Sportradar virtual sports betting page screenshot with populated bet slip

Uplink MCP File Automation

Shipped an MVP-style Claude Code for files: a research CLI for testing MCP workflow limits, filesystem-tool safety, and agent design from no-library prototypes to SDK-based builds.

Outcomes
  • Natural-language file operations
  • Measured token and tool-scaling limits
  • Reusable local and remote workflows
Role
Open Source Creator & Maintainer
MCP Inspector showing Uplink file automation tools

AI-Assisted Trading Interface

LinkNDA protected

Currently working on an AI-assisted trading dashboard for professional traders, connecting custom market views, voice input, Interactive Brokers workflows, and validated command routing. Most of the full-stack work is NDA-protected, so the chart preview only hints at the decision support and automation behind it.

Outcomes
  • Clearer live market context
  • Faster entry and exit decisions
  • Custom workflow for trader edge
Role
Full-Stack AI Product Engineer
Trading interface chart screenshot with price line and volume bars

What I help teams build

I help turn messy product surfaces into maintainable React systems, practical internal tools, and workflows teams can keep shipping.

  • Building an AI-Powered CLI for File Operations

    How I designed an AI-powered CLI for file operations using MCP, agentic workflows, and developer-focused automation across local and remote systems.

    Read article
    AI12m read
  • Surveying the Agent Ecosystem: MCP, LLMs, and Cloud Files

    A survey of MCP agents, LLM tooling, and cloud file workflows to identify gaps in real-world file automation across local and remote systems.

    Read article
    AI16m read
  • Technologies for a Local-First MCP Host Application

    Why I chose TypeScript, Bun, Docker, Ollama, and a local-first architecture for an MCP host application for AI-assisted file workflows.

    Read article
    AI11m read
  • Uplink: A Modular MCP-Powered CLI for File Operations

    How I built a modular MCP-powered CLI for file operations with local and remote agents, tool orchestration, guardrails, and extensible architecture.

    Read article
    AI21m read