AI-powered size and fit recommendations for e-commerce fashion brands
Sizebay solves fit-related returns through anthropometric AI and virtual fitting rooms integrated into e-commerce platforms. The stack spans computer vision (DINOv2, CLIP, Stable Diffusion), commerce APIs (Shopify, VTEX, WooCommerce), and analytics (Looker, SQL), with recent adoption of ClickHouse and Qdrant suggesting a shift toward vector-based recommendation pipelines at scale. Active projects center on client integrations and returns API work, while the sales-heavy hiring mix (6 sales vs. 3 engineering) and focus on "driving growth of thousands of online stores" indicates a land-and-expand strategy targeting mid-market fashion retailers.
Notable leadership hires: Integration Lead
Sizebay is a fashion-tech platform that reduces return rates by predicting clothing fit. The core offering derives body measurements from user inputs (gender, height, weight, age) and compares them against manufacturer specs to recommend the correct size and highlight similar items in different fits. The product integrates via plugins into Shopify, VTEX, WooCommerce, and custom e-commerce stacks. Founded in 2014 and based in Austin, the 51–200-person team serves thousands of online retailers globally, with current hiring expansion focused on Brazil. Key operational challenges include scaling integrations, improving recommendation accuracy, and supporting customer success at scale.
Sizebay natively integrates Shopify, VTEX, and WooCommerce. Custom integrations via REST APIs support additional platforms; returns API integration is actively in development.
The platform uses DINOv2, CLIP, Stable Diffusion, and Flux for computer vision and image synthesis. OpenAI APIs are also in the stack. ClickHouse and Qdrant adoption indicates vector-based recommendation scaling.
Other companies in the same industry, closest in size