Lead Inference Engineer - End-to-End Deployment on Kubernetes

Hyperbolic Labs; San Francisco (CA); On-site; USD 150,000 - 210,000; Full time

Job summary

Hyperbolic Labs is hiring an Inference Engineer to build end-to-end inference capabilities on Forge and our Kubernetes platform. You will deploy and serve models across global clusters on heterogeneous hardware, ensuring production readiness with monitoring, gateways, and endpoints.

Ideal candidates bring a strong inference background, hands-on Kubernetes production experience, and expertise in optimization, autoscaling, and debugging performance issues across distributed systems.

Qualifications

• Strong inference background covering end-to-end path from request to token
• Proven experience operating production Kubernetes clusters
• Experience with inference across heterogeneous hardware

Responsibilities

• Deploy and serve models across Forge and Kubernetes environments
• Evaluate inference frameworks and set up monitoring, gateways, and endpoints
• Advance optimization, autoscaling, KV-cache orchestration, and debugging for production workloads

Skills

Kubernetes

Distributed deployment

Inference optimization

Model deployment

Monitoring/telemetry

NVIDIA Dynamo

KV cache

Production infrastructure

Tools

Kubernetes tooling

Monitoring tools

Deployment tooling

Job description

Hyperbolic Labs is hiring an Inference Engineer to build end-to-end inference capabilities on Forge and our Kubernetes platform. You will deploy and serve models across global clusters on heterogeneous hardware, ensuring production readiness with monitoring, gateways, and endpoints.

Ideal candidates bring a strong inference background, hands-on Kubernetes production experience, and expertise in optimization, autoscaling, and debugging performance issues across distributed systems.