YS
Senior Backend Engineer, Inference Platform
York Space SystemsNew York, NY · Remote · full time · Senior
$200,000 – $250,000
Listed on York Space Systems’s own careers site. You apply with them directly — we never stand between you and the employer.
What this role is
You'll design and operate the inference gateway that intelligently routes every model call across hosted providers and internal models, optimizing for cost, latency, and availability while building the control plane to manage access, performance, and billing. This role sits at the intersection of infrastructure and product, requiring deep expertise in model serving internals and the ability to ship changes safely in production with single-digit-millisecond budgets.
Our summary, not York Space Systems’s wording. The full posting is on their site.
What they ask for
Required
- Production experience with model serving platforms like vLLM or SGLang
- Understanding of continuous batching, KV caching, and prefix caching tradeoffs
- Experience tuning serving stacks against live traffic
- Fluency with provider APIs including tokenization and prompt-caching semantics
- Experience building or operating a proxy, gateway, or data plane handling production traffic
- Ability to handle streaming responses including partial state and mid-stream failures
- Backend generalist proficiency in Python and Kubernetes
Nice to have
- Experience at an inference provider or GPU cloud
- Contributions to open-source serving stacks
- Fine-tuning and evaluating models in production
- Usage metering, billing, or cost optimization at scale