AI Figma-to-Code Generation Engineer

Nolvex Studio

Remote · $100k – $130k / year · Full-time · Posted 5 months ago

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

About the role

Designers hand off pixel-perfect Figma files. Developers spend 3 days turning them into responsive code that never quite matches the design. Our tool closes this gap — it reads Figma designs and generates production-ready frontend code that matches the original within 2 pixels. The hard part isn't generating HTML; it's understanding design intent: which elements are interactive, how components reflow on smaller screens, and where the designer used a system token versus a one-off value. You'll build the design understanding layer: the vision models that parse Figma frames into semantic components, the layout analysis that infers responsive behavior, and the style extraction that maps visual properties to design system tokens. Each improvement gets measured by developer acceptance rate — what percentage of generated code ships without manual editing. The design-to-code team is five engineers. You'll work between the Figma plugin developer who handles data extraction and the code generation engineer who produces the output. Your semantic understanding layer is the bridge that makes the output intelligent rather than mechanical.

Fully remote.

Responsibilities

Build vision models that parse Figma frames into semantic UI components
Design layout analysis inferring responsive behavior from static designs
Implement style extraction mapping visual properties to design system tokens
Measure and improve developer acceptance rate of generated code
Handle edge cases: overlapping elements, auto-layout inference, variant detection
Collaborate with code generation team on component abstraction quality

Requirements

3+ years in computer vision or document understanding
Experience with layout analysis or UI component detection
Strong PyTorch skills for model development
Understanding of frontend development concepts: responsive design, component systems
Interest in design tools and developer experience