Remote Senior AI Infrastructure Engineer - GPU & Model Serving

BragDev; United States; À distance; USD 180 000 - 260 000; Plein temps

Résumé du poste

BragDev is seeking a Senior AI Infrastructure Engineer (GPU and Model Serving) for remote work in the U.S. You will design and maintain the infrastructure powering AI workloads, including GPU clusters and low-latency model serving.

You will optimize autoscaling, cost, and reliability, partnering with teams across ML, data, and platform to ensure robust, scalable inference in production.

Qualifications

• Experience deploying GPU clusters and low-latency model serving.
• Strong background in autoscaling inference and cost control.
• Experience in distributed ML systems and reliability practices.

Responsabilités

• Run the infrastructure behind AI workloads including GPU clusters and model serving.
• Implement reliability practices and autoscaling for inference.
• Collaborate with ML, data, and platform teams to ensure scalable production workloads.

Connaissances

Python

AWS

PyTorch

MLOps

Distributed Systems

GPU clusters

Description du poste

BragDev is seeking a Senior AI Infrastructure Engineer (GPU and Model Serving) for remote work in the U.S. You will design and maintain the infrastructure powering AI workloads, including GPU clusters and low-latency model serving.

You will optimize autoscaling, cost, and reliability, partnering with teams across ML, data, and platform to ensure robust, scalable inference in production.