Want to know if this job is worth applying to?
San Francisco, California, United States
Onsite
Hyperbolic Labs is on a mission to democratize AI by breaking down the barriers to computing power with our Open-Access AI Cloud. By making better use of idle computing resources across the globe, we offer an innovative GPU marketplace and AI inference service that promise affordability and accessibility for all. As pioneers at the intersection of AI and open-source technology, we believe in an open future where AI innovation is limited only by imagination, not by access to resources. We're looking for forward-thinking individuals who share our passion for making AI universally accessible, secure, and affordable. Join us in building a platform that empowers innovators everywhere to turn their visionary AI projects into reality.
We're looking for an Inference Engineer to build inference capabilities on top of Forge, our unified control plane, so customers can consume model tokens without managing GPUs and our NeoCloud partners get a full-stack path to their own token-factory offering. You'll own how models get deployed and served across clusters distributed around the world, on heterogeneous hardware.
Deployment comes first: serving models on Forge and our Kubernetes offering, evaluating inference frameworks, and standing up the monitoring, gateways, and endpoints that make a deployment production-ready. From there the work expands into optimization, autoscaling, KV-cache orchestration, and customer inference debugging. This is the primary seat for inference at Hyperbolic \u2014 you'll build it end to end, with real influence over where the scope lands.
Strong general inference background with a broad, high-level command of the stack rather than a narrow specialty — you can reason about the whole path from request to token
Deep Kubernetes experience, including hands-on ability to operate clusters in production, not just deploy to them
Solid grasp of the concepts that govern inference performance: TTFT, disaggregated inference, speculative decoding, and KV cache and its inner workings
Familiarity with modern inference frameworks and serving engines, and the judgment to evaluate and select among them for a given workload
Working knowledge of NVIDIA Dynamo and how it fits into a distributed serving architecture
Experience setting up monitoring, gateways, and endpoints for production inference services
Proven ability to build a product end to end — you've taken something from nothing to serving real traffic
Strong self-initiative and comfort operating as the primary owner of an area with minimal direction
Generalist instincts: you're willing to pick up adjacent work when it's what the product needs
Experience spanning both inference deployment and inference optimization
Hands-on model optimization work — quantization, batching strategies, kernel-level tuning, or similar
Understanding of RDMA and high-performance networking as they apply to 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
Hyperbolic is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees.
