UX Designer (React Prototyping)

Norton Blake; Greater London; Hybrid; GBP 66,000 - 92,000; Part time

Job summary

Norton Blake is seeking a UX designer for a 3-month London-based hybrid role focused on prototyping AI-powered experiences in code. You will design AI-driven interactions, build high-fidelity React prototypes, and iteratively test concepts with real users.

The role requires hands-on JavaScript, HTML, CSS, and advanced Figma skills, plus MCP experience to connect models with data-aware interfaces. You will work across engineering and data science teams to ship AI features.

Qualifications

• Portfolio of live, coded prototypes (not static Figma files)
• Proficiency in JavaScript, HTML and modern responsive CSS with React
• Advanced Figma skills: variables, auto-layout, prototyping, design tokens
• Experience designing AI workflows that connect models to interfaces
• Practical experience with agent building or AI output evaluation

Responsibilities

• Design interactions for AI-driven products and prototyping
• Build high-fidelity coded prototypes in React
• Use AI tooling to prototype and iterate quickly
• Create reusable AI pattern components aligned to the design system
• Collaborate with engineers, architects and data scientists
• Explain technical trade-offs to non-technical stakeholders

Skills

JavaScript

React

HTML

CSS

Figma

Design systems

Tokens

MCP experience

AI tooling

Tools

Figma

Cursor

Kiro

Claude Code

Job description

UX designer (React Prototyping), 3 months, London/Hybrid, £425/day (Inside IR35)

The role in one line

A designer who codes (or an engineer who designs) to act as the catalyst for the client's new AI Community of Practice - prototyping AI-powered experiences in working code, and embedding AI into how the design teams themselves work.

What they'll actually do

• Design interactions for AI-driven products: chat, generative tools, recommendation systems, agentic flows
• Build high-fidelity coded prototypes in React to test concepts with real customers
• Use AI tooling (Figma, Cursor, Kiro, Claude Code, custom plugins) to prototype and iterate at speed
• Build reusable AI pattern components - prompt inputs, chat, data visualisation, agent workflows - aligned to the existing design system
• Work across engineers, architects and data scientists, and bring their workflows into the design practice
• Explain technical trade-offs to non-technical stakeholders

Non-negotiables - screen hard on these

1. A portfolio of live, coded prototypes. Not static Figma files, not case-study write-ups. Shipped AI features preferred.
2. JavaScript, HTML, modern responsive CSS, React. Hands-on and current.
3. Advanced Figma. Variables, auto-layout, prototyping, design systems and tokens.
4. MCP experience. Designing AI workflows that connect models to interfaces with context-aware data flow.
5. Agent building or AI output evaluation. Practical, with a considered view on where AI falls short.