Project Engineer – AI Vision & Real-Time Inference

Encore Automation, LLC; Auburn Hills (MI); On-site; USD 100,000 - 140,000; Full time

Job summary

Encore Automation, LLC seeks a talented Deep Learning Engineer to design and deploy models for automated paint inspection in a production setting. You will optimize real-time inference pipelines, reduce latency, and maximize GPU utilization across multi-plant deployments.

Responsibilities include preprocessing large-scale datasets, integrating AI models into existing systems, and refining architectures for performance and scalability.

Qualifications

• Experience designing and deploying Deep Learning models.
• Experience with automated defect detection or computer vision systems.
• Experience optimizing real-time inference pipelines.
• Experience working with GPU hardware for model deployment.
• Experience integrating AI models into existing systems.
• Experience building end-to-end ML workflows.
• Experience optimizing model architectures for performance and scalability.
• Experience handling and preprocessing large-scale datasets.
• Experience supporting training and testing pipelines.

Responsibilities

• Design and deploy Deep Learning models for automated paint inspection in production.
• Streamline real-time inference pipelines to minimize latency at plant level.
• Integrate AI models into existing systems and workflows from data ingestion to inference.
• Refactor model architectures and optimize hardware utilization for multi-plant scalability.
• Label and preprocess massive datasets to support robust training and testing pipelines.

Skills

Deep Learning

Computer Vision

GPU Deployment

ML Pipelines

End-to-end ML

Education

Master's degree (preferred)

Tools

PyTorch

TensorFlow

GPU Hardware

Job description

Encore Automation, LLC seeks a talented Deep Learning Engineer to design and deploy models for automated paint inspection in a production setting. You will optimize real-time inference pipelines, reduce latency, and maximize GPU utilization across multi-plant deployments.

Responsibilities include preprocessing large-scale datasets, integrating AI models into existing systems, and refining architectures for performance and scalability.