End-to-End Inference Engineer — Kubernetes & Optimization

Hyperbolic; San Francisco (CA); Hybrid; USD 180,000 - 240,000; Full time

Job summary

Hyperbolic is seeking an experienced Inference Engineer to build and run inference on Forge and our multi-cluster platform across the globe. You will own how models are deployed and served across clusters, with emphasis on production reliability and cross-region scalability.

Responsibilities include evaluating inference frameworks, standing up monitoring, gateways, and endpoints, and optimizing performance, batching, and KV-cache orchestration toward a robust, scalable service.

Qualifications

• Evidence of end-to-end deployment of inference services.
• Experience running production Kubernetes clusters.
• Familiar with inference frameworks and serving engines.
• Experience building products for real traffic.

Responsibilities

• Own deployment of models across global clusters.
• Set up monitoring, gateways, and endpoints for production inference.
• Optimize inference performance and autoscaling.
• Evaluate frameworks and select best fit for workloads.

Skills

Inference background

Kubernetes

Distributed serving

Monitoring

Product ownership

Self-initiative

Generalist mindset

Tools

NVIDIA Dynamo

RDMA networking

Kubernetes tooling

Serving frameworks

Job description

Hyperbolic is seeking an experienced Inference Engineer to build and run inference on Forge and our multi-cluster platform across the globe. You will own how models are deployed and served across clusters, with emphasis on production reliability and cross-region scalability.

Responsibilities include evaluating inference frameworks, standing up monitoring, gateways, and endpoints, and optimizing performance, batching, and KV-cache orchestration toward a robust, scalable service.