GPU Infra & MLOps Engineer — Scalable Inference

Cehpoint; United States; Remote; USD 13,000 - 22,000; Full time

Job summary

Cehpoint AI is hiring for a role focused on deploying and scaling model-serving workloads on GPU infrastructure. You will monitor latency, cost per request, and failure rates while automating deployment, backups and alerts to ensure high availability.

You will contribute to sizing studies for power, cooling and GPU capacity for the planned facility in West Bengal, working with Linux, containers, and production-grade model serving systems.

Qualifications

• Experience administering Linux systems in production environments.
• Knowledge of containerization and production model serving.
• Understanding of performance implications of GPU memory, batching and quantisation.

Responsibilities

• Deploy, scale and monitor model-serving workloads on GPU servers.
• Measure cost per request, latency and failure rates, and bring them down.
• Automate deployment, backups and alerting so the platform stays up.

Skills

Linux administration

Container orchestration

Model serving in production

GPU memory management

Batching

Quantisation

Job description

Cehpoint AI is hiring for a role focused on deploying and scaling model-serving workloads on GPU infrastructure. You will monitor latency, cost per request, and failure rates while automating deployment, backups and alerts to ensure high availability.

You will contribute to sizing studies for power, cooling and GPU capacity for the planned facility in West Bengal, working with Linux, containers, and production-grade model serving systems.