Computer Vision Engineer — Visual Search & Discovery

We are a fashion discovery platform with 6.2 million users and 3,400 brand partners. Visual search is central to our product, and our current contrastive learning model performs poorly on long-tail catalogue imagery with inconsistent backgrounds, lighting, and angles. We are hiring a contract Computer Vision Engineer for a 10-month engagement to improve similarity search performance on long-tail images and build evaluation infrastructure to measure improvements systematically.

• Improve similarity search performance on long-tail catalogue imagery.
• Enhance the existing contrastive learning-based visual search pipeline.
• Build evaluation test sets and metrics to systematically measure model improvements.
• Collaborate with cross-functional teams to integrate model changes into the product.

• Proven experience in computer vision and deep learning.
• Strong understanding of contrastive learning and similarity search methods.
• Experience building evaluation infrastructure for ML models.
• Proficiency in Python and deep learning frameworks such as PyTorch or TensorFlow.
• Ability to work independently in a remote, contract environment.

• Experience with fashion e-commerce or visual discovery platforms.