Inference Engineer, Global GPU Deployment & Kubernetes

Hyperbolic; San Francisco (CA); On-site; USD 140,000 - 230,000; Full time

Job summary

Hyperbolic Labs in San Francisco seeks an Inference Engineer to build and scale inference on Forge and our Kubernetes stack, enabling customers to run models without managing GPUs. You’ll own deployment, monitoring, and endpoints across global clusters on heterogeneous hardware.

You’ll expand into optimization, autoscaling, KV-cache orchestration, and debugging real traffic. The role combines hands-on engineering with product ownership and requires a broad, systems-level view of the inference

Qualifications

• Strong general inference background covering deployment to token serving.
• Hands-on Kubernetes in production environments.
• Experience with inference frameworks and serving engines.
• Experience with distributed serving architectures.

Responsibilities

• Deploy models on Forge and Kubernetes for production serving.
• Evaluate inference frameworks and set up monitoring, gateways, and endpoints.
• Optimize performance with autoscaling and KV-cache orchestration.
• Debug inference issues and support customers.

Skills

Inference stack

End-to-end ownership

System design

Performance tuning

Tools

Kubernetes

NVIDIA Dynamo

RDMA networking

Monitoring tools

Job description

Hyperbolic Labs in San Francisco seeks an Inference Engineer to build and scale inference on Forge and our Kubernetes stack, enabling customers to run models without managing GPUs. You’ll own deployment, monitoring, and endpoints across global clusters on heterogeneous hardware.

You’ll expand into optimization, autoscaling, KV-cache orchestration, and debugging real traffic. The role combines hands-on engineering with product ownership and requires a broad, systems-level view of the inference