AI Predictive Tool Wear Detection Engineer

Daeva Tech

On-site · $130k – $160k / year · Full-time · Posted 3 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

Vibration sensors, thermal cameras, and spindle load data feed into everything we build at Daeva Tech. If you're comfortable fusing multiple sensor streams into a single model and shipping it to run on a factory floor, this role is built for you. You'll design and deploy models that predict cutting tool wear before it causes scrap parts or unplanned downtime, working from raw sensor streams through to a dashboard our floor supervisors check every shift. Deployment happens on edge hardware on-site, not just in the cloud, so you'll own the full path from training to containerized inference at the plant. This is interesting work because the failure modes are physical and immediate — a wrong prediction means a bad part or a stopped line, and you'll see the impact of your models within days, not quarters.

Responsibilities

Design predictive models for cutting tool wear from multi-sensor input streams
Deploy containerized inference to on-site edge hardware
Build monitoring dashboards for floor supervisors to track tool health
Collaborate with plant engineers to validate predictions against physical tool inspections
Optimize model latency for real-time production line constraints

Requirements

Experience with computer vision or sensor-fusion modeling in an industrial setting
Strong PyTorch skills and comfort with Docker-based deployment
Willingness to work on-site at our manufacturing facility
Experience with AWS for model training infrastructure
Background in predictive maintenance is a strong plus