Founding Computer Vision ML Engineer — Production-Ready & Equity

Moe; United States; Sur place; USD 200 000 - 260 000; Plein temps

Résumé du poste

Moe is seeking a senior machine learning engineer to lead fine-grained item identification, from model selection through production deployment. You will own the end-to-end CV stack, define success metrics, and collaborate with labeling teams to improve accuracy across Moe's catalog.

You will shape the evaluation framework, determine where to invest for broader coverage or deeper accuracy, and communicate tradeoffs to investors and internal teams.

Qualifications

• 5+ years of applied computer vision
• Hands-on experience with fine-grained/instance-level classification
• Experience shipping models to production at scale
• Strong ability to define evaluation metrics and success criteria
• Excellent communication to non-technical stakeholders

Responsabilités

• Design and own the computer vision architecture for fine-grained item identification — brand, model, edition, variant.
• Define what 'accurate enough' means per category, and build calibrated confidence scoring.
• Build the feedback loop between model errors and the labeling pipeline.
• 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 model capabilities to the company, investors, and customers when needed.

Connaissances

Applied computer vision

Fine-grained/instance-level

Production ML systems

Model evaluation frameworks

Communication with stakeholders

Outils

PyTorch

TensorFlow

Description du poste

Moe is seeking a senior machine learning engineer to lead fine-grained item identification, from model selection through production deployment. You will own the end-to-end CV stack, define success metrics, and collaborate with labeling teams to improve accuracy across Moe's catalog.

You will shape the evaluation framework, determine where to invest for broader coverage or deeper accuracy, and communicate tradeoffs to investors and internal teams.