Member of Technical Staff - Inference

The role

You will build inference capabilities on Forge to allow customers to consume model tokens. You will own how models are deployed and served across distributed clusters on heterogeneous hardware.

What you will do

• Serve models on Forge and Kubernetes offering
• Evaluate inference frameworks
• Stand up monitoring, gateways, and endpoints for production-ready deployment
• Perform optimization, autoscaling, and KV-cache orchestration
• Perform customer inference debugging

Required qualifications

• Strong general inference background with a broad, high-level command of the stack
• Deep Kubernetes experience including hands-on ability to operate clusters in production
• Solid grasp of TTFT, disaggregated inference, speculative decoding, and KV cache
• Familiarity with modern inference frameworks and serving engines
• Working knowledge of NVIDIA Dynamo and distributed serving architecture
• Experience setting up monitoring, gateways, and endpoints for production inference services
• Proven ability to build a product end to end
• Strong self-initiative and comfort operating as the primary owner with minimal direction
• Generalist instincts

Nice to have

• Experience spanning both inference deployment and inference optimization
• Hands-on model optimization work such as quantization, batching strategies, or kernel-level tuning
• Understanding of RDMA and high-performance networking for distributed serving
• Experience deploying inference across heterogeneous accelerators
• Background supporting customers directly on inference debugging and performance issues
• Experience at a GPU cloud, inference provider, or AI infrastructure company

About the company

Hyperbolic makes global AI compute liquid by bringing fragmented, heterogeneous GPU capacity together into one unified platform. They are building toward a future where compute flows as freely as electricity.