Computer Vision Engineer — Image Vectorization & SVG Path Optimization

We run a free online image vectorizer (turns raster images like PNG/JPG into clean SVG vector files). We tested our output against a competitor and it was dramatically different — 29x larger files, jagged edges, thousands of unnecessary points where the competitor drew a simple clean shape. The core problem: our tool doesn't recognize basic shapes like circles and rectangles, so it clumsily traces around them instead of drawing them properly. We need someone to fix this using classical computer vision (no AI/machine learning needed) — teach the tool to recognize shapes and simplify messy output into clean, minimal paths. We also need three output modes for different customers: a "cutting" mode for Cricut/laser/embroidery machines (super clean, minimal points, exports to DXF), a "print" mode for products like t-shirts (solid colors, checks how big it can print), and an "edit" mode for designers (organized, easy to tweak). You'd be building this as a standalone service — image goes in, files and quality stats come out. Someone else handles the website around it. We have a real benchmark image and clear pass/fail criteria ready, so this is well-defined, testable work.