Bond Studio AI

We’re building a web platform that lets users take photos of real rooms and see photorealistic visualizations of products placed inside those spaces using modern image generation.

This is a core product experience, not a demo. The output quality matters, the UX matters, and the system needs to scale to real users.

We’re hiring a full-stack engineer to own delivery of this experience end-to-end, embedded directly with our internal engineering team.

You'll be asked to deliver:
- User-driven image generation flows
- Photorealistic room visualizations using Google's Nano Banana
- Backend services to manage generation jobs, prompts, inputs, outputs, and metadata
- The database to store this data
- Frontend experiences for browsing, regenerating, and comparing generated images

This is an engineering-heavy role - you’ll be designing systems, not just wiring up APIs.

*We care less about years of experience and more about proof you've built something real using LLMs or image generation.*

You should have:
- Demonstrable experience using LLMs or image generation APIs in a real project
- Comfort owning features end-to-end (backend, frontend, data model)
- Strong TypeScript fundamentals
- Solid product instincts  (you can reason about UX, not just code)
- Experience shipping production features, not just prototypes

Bond Studio makes software that lets users capture their space with their phone and see a visualization of how that room could look if it were remodeled.  Users can browse products, select them, and see them visualized in their space.  

Part of this experience is search where users can type in queries and see products based on their query.  Currently this functionality is powered by a custom Python service that contains an index of all of our products and leverages LLMs to provide results to users.
Search quality and speed are critical to the overall user experience.
We have a comprehensive benchmark for this service and are looking to work with a software engineer to improve its performance on this benchmark.

This is not a greenfield project. You will be working with an existing production system and are expected to diagnose bottlenecks, propose improvements, and implement measurable gains.

You will analyze and improve a real-world product search system that includes:

A large, structured product catalog with many attributes and variants.
User-driven filtering and refinement (dimensions, style, finish, price, etc.).

Natural-language queries interpreted by an LLM-backed layer.
 

A backend search service that must be fast, stable, and scalable.
 

The focus of this engagement is on result quality while maintaining acceptable performance.