I'm Colombian, based in Bogotá, and I grew into product work through a mix of design, engineering, client strategy, and marketing. That range is the point: I can talk to users, design the interface, understand the funnel, and still sit inside the codebase.
I build high-fidelity prototypes in Figma and Framer, then ship production UI in Vue or React with the backend and data work to support it. Node, Python, Ruby, Postgres, Mongo, APIs, and deploy pipelines are all familiar terrain.
Lately my workflow has become much more AI-assisted: Claude Code for codebase work, GPT and Gemini for reasoning and research, Cursor for daily implementation, and MCPs to connect agents to real project tools like GitHub, Supabase, Postman, and browser context.
When I'm not at a screen I'm usually on a gravel bike, playing golf, or testing a new workflow to see whether it is useful after the hype wears off.
A short timeline.
The roles, in order. Happy to walk you through any of them.
Led design for an AI-powered loan origination system, working through user research, ideation, design-system execution, and React-facing product decisions.
Worked with a 12+ developer team on a wholesale cannabis platform, including Vue 3, Vite, TypeScript, tests, and a Vue 2 to Vue 3 migration.
Led frontend development for Shopify marketing automation and analytics apps. Designed features in Figma and maintained the Vue, Nuxt, Tailwind, Ruby on Rails, and serverless stack.
Built emails, landing pages, web apps, and automation for clients including Zebra, HP, Wacom, and Motorola using React, Python, and Django.
Founded a Bogotá creative studio across design, development, and marketing. Led 10+ projects and closed 20+ clients through sales and client strategy.
Worked at a Bogotá tech incubator building and maintaining projects with JavaScript, Sass, HTML, PHP, and Laravel while collaborating directly with clients.
What I'm into this week.
I keep this honest, on a low-stakes schedule. Updated whenever it stops being true.
A hybrid profile, on purpose.
The useful part is not just knowing many tools. It is knowing which layer of the product needs attention next.
I start in the product problem, not the file format. That might become a Figma prototype, a Framer flow, a Vue screen, or a small automation that proves the idea faster.
Because I can ship the interface myself, I catch constraints early: API shape, loading states, events, permissions, analytics, and the details that make a handoff real.
AI is part of my daily workflow now: Claude Code for repo work, GPT and Gemini for reasoning, Cursor for implementation, and MCPs to connect agents to real tools.