🛠 Tech Stack

💼 About This Role

You'll build computer vision models for Mill Commercial, turning food waste streams into operational intelligence for commercial kitchens. You'll own training pipelines, evaluate edge models, and help design LLM-powered product features that deliver customer-facing recommendations.

🎯 What You'll Do

• Build end-to-end ML training pipeline for edge computer vision models.
• Train segmentation, classification, and mass-estimation models for camera pipeline.
• Build cloud-side evaluation harness to monitor deployed model performance.
• Own MLOps: experiment tracking, model versioning, automated evaluation.
• Export and validate models for edge deployment, optimizing with edge team.

📋 Requirements

• Strong fundamentals in computer vision and deep learning (segmentation, detection, classification).
• Fluency with VLMs, LLMs, foundation models, and agentic systems.
• Experience building ML training pipelines and data annotation systems at scale.
• Experience evaluating ML models rigorously with metrics and eval harnesses.
• Proficiency with cloud ML infrastructure (AWS or equivalent) for training and data pipelines.

✨ Nice to Have

• Video understanding (temporal consistency, tracking, video segmentation).
• Foundation models for data annotation.
• MLOps tooling (Weights & Biases, MLflow, SageMaker).
• Shipping LLM- or agent-powered features in a product.

📨 Hiring Process

Estimated timeline: 2-3 weeks · AI estimate

1. 1Recruiter phone screen· 30 min
2. 2Technical interview· 60 min
3. 3Hiring manager interview· 45 min