Inference Engineer — Global GPU Cloud & End-to-End Deploy

Hyperbolic; San Francisco (CA); On-site; USD 160,000 - 210,000; Full time

Job summary

Hyperbolic is building an Open-Access AI Cloud to democratize AI by unlocking GPU resources and scalable inference. We are seeking an Inference Engineer to own deployment and serving across global clusters on Forge and Kubernetes, optimizing performance and reliability.

You will lead end-to-end deployment, monitoring, and debugging, with responsibility for KV cache orchestration and operational excellence in a distributed serving architecture.

Qualifications

• Strong inference background across deployment and optimization.
• Hands-on Kubernetes production operations.
• Experience with production monitoring and endpoints.
• Ability to own product areas with minimal direction.

Responsibilities

• Deploy models on Forge and Kubernetes offerings, and evaluate inference frameworks.
• Set up monitoring, gateways, and endpoints for production inference services.
• Optimize, autoscale, and orchestrate KV caches for efficient inference.
• Debug inference issues end-to-end and own the feature scope.

Skills

Kubernetes in prod

Inference background

Performance optimization

End-to-end product ownership

Self-initiative

Distributed systems

Tools

NVIDIA Dynamo

Monitoring systems

GPU cloud platforms

Job description

Hyperbolic is building an Open-Access AI Cloud to democratize AI by unlocking GPU resources and scalable inference. We are seeking an Inference Engineer to own deployment and serving across global clusters on Forge and Kubernetes, optimizing performance and reliability.

You will lead end-to-end deployment, monitoring, and debugging, with responsibility for KV cache orchestration and operational excellence in a distributed serving architecture.