Senior Backend Engineer, Inference Platform

Inference Gateway Control Plane EngineerAt You.com, we are building the AI Search Infrastructure that powers modern AI systems. Our goal is to create the trusted knowledge layer that agents, applications, and enterprises rely on to retrieve real-time, accurate, and citation-backed information.Our platform combines proprietary vertical indexes with LLM-optimized retrieval systems to power AI agents, applications, and enterprise workflows. We are solving hard problems across search, large language models, and large-scale infrastructure to make AI systems more reliable, transparent, and useful.Our team includes engineers, researchers, product builders, and operators who care about solving meaningful problems and delivering real-world impact. Whether you are improving core infrastructure, shaping product experiences, or helping bring new AI capabilities to market, your work will help define how modern AI finds and uses knowledge.Every model call from our products and customers passes through one layer: our inference gateway. It allows users to select a model and we intelligently route the call to optimize on cost, latency, and high availability. We are now building the control plane above it, to manage and govern access, performance, and cost.You will own and scale that gateway. The work sits between model serving and product: routing and fallback across hosted providers and our own models, cache-aware routing decisions, metering accurate enough to bill on, and enforcement on the request path within a single-digit-millisecond budget.This is a remote position open to candidates based anywhere in the United States. We give preference to candidates in the San Francisco Bay Area or New York, where we have offices, but we are happy to consider strong remote candidates elsewhere in the US.ResponsibilitiesOwn the inference gateway that every model call routes through, including provider and model selection, fallback, and capsBuild intelligence layer to autonomously pick the right model for the right turn in the taskMake routing decisions that account for prefix-cache behavior, batching, and time to first token, not only price and availabilityBuild cost attribution and metering across providers, including cached-token accounting, accurate enough to bill and enforce onBuild request-path enforcement that degrades gracefully and never takes down a customer's inference callShip inference-time changes in shadow mode first, with the measurement to prove they workQualificationsHands-on production experience with model serving on stacks such as vLLM, SGLang (or similar platforms), with a working understanding of continuous batching, KV and prefix caching, and the tradeoff between time to first token and throughputYou have tuned a serving stack against live traffic and know what moves p99 in practice, not only in theoryFluency across provider APIs: tokenization, prompt-caching semantics, and the differences in how usage and cached tokens are reported and pricedExperience building or operating a proxy, gateway, or data plane on the critical path of production traffic, with sound instincts for failing openComfort with streaming responses and the parts that get awkward: partial state, mid-stream failures, and work that can only happen once the stream closesA strong backend generalist (Python, Kubernetes). We expect you to pick up whatever you have not touched yetWe weigh trajectory and recent growth more heavily than years of experienceOur salary bands are structured based on a combination of geographic tiers and internal leveling. Compensation is determined by multiple factors assessed during the interview process, with the final offer reflecting these considerations.Salary Band $200,000 —$250,000 USD Y.O.U.