AI Defect Detection Pipeline Engineer

Ontix Intelligence

Hybrid · $80k – $100k / year · Full-time · Posted 5 months ago

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

About the role

Factory floors generate images at a pace that would overwhelm any human inspector — 200 cameras capturing 4,000 images per minute across three manufacturing lines. Our computer vision system processes every frame, detects defects as small as 0.1mm, and triggers real-time alerts before defective parts move downstream. The models work. The problem is keeping them working. Manufacturing environments are hostile to ML models. Lighting changes with the weather, camera lenses fog up, product variants shift quarterly, and a new defect type appears every few weeks. You'll build the pipeline infrastructure that keeps our detection models accurate despite these shifts: automated retraining triggers, data quality monitoring, model versioning, and drift detection — all running 24/7 with zero tolerance for downtime. You'll split time between our Chicago office (for factory visits and hardware integration) and remote work. The CV team is six engineers; you'll focus on the operational ML infrastructure while others handle model architecture.

Responsibilities

Build automated retraining pipelines triggered by performance degradation
Implement data quality monitoring for factory camera feeds
Design model versioning and rollback systems for production deployments
Create drift detection alerts for changing manufacturing conditions
Optimize inference pipeline for real-time processing at 4,000 images per minute
Coordinate with factory operations teams during model updates

Requirements

3+ years in ML engineering with computer vision deployment experience
Experience building MLOps pipelines: training, evaluation, deployment, monitoring
Proficiency with Docker, MLflow, and cloud services
Understanding of manufacturing or industrial automation environments
Comfort with on-site visits to factory environments