Founding ML Engineer, Computer Vision (Object Detection)

Moe is building a product that identifies items from photos and prices them accurately. The Founding ML Engineer will set the technical direction for computer vision-based item identification, own model architecture and data strategy, and take models from research to reliable production deployment. The role will also establish accuracy standards, confidence scoring, feedback loops, and category expansion plans.

Responsibilities:

• Design and own the computer vision architecture for fine-grained item identification — brand, model, edition, variant — starting from foundation vision models and fine-tuning toward Moe's specific catalog
• Define what "accurate enough" means per category, and build calibrated confidence scoring so the product can say "we're not sure" instead of guessing
• Build the feedback loop between model errors and what gets labeled next, in partnership with the labeling lead
• Decide where to invest: broader category coverage vs. deeper accuracy on today's categories
• Own the model serving path from research to production — latency, cost, and reliability at scale
• Represent the identification model's capabilities and limits to the rest of the company, including in investor and customer conversations when needed