Senior Backend Engineer, Inference Platform

About the Role

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.

Responsibilities

• Own the inference gateway that every model call routes through, including provider and model selection, fallback, and caps
• Build intelligence layer to autonomously pick the right model for the right turn in the task 
• Make routing decisions that account for prefix-cache behavior, batching, and time to first token, not only price and availability
• Build cost attribution and metering across providers, including cached-token accounting, accurate enough to bill and enforce on
• Build request-path enforcement that degrades gracefully and never takes down a customer's inference call
• Ship inference-time changes in shadow mode first, with the measurement to prove they work

Qualifications

• Hands-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 throughput
• You have tuned a serving stack against live traffic and know what moves p99 in practice, not only in theory
• Fluency across provider APIs: tokenization, prompt-caching semantics, and the differences in how usage and cached tokens are reported and priced
• Experience building or operating a proxy, gateway, or data plane on the critical path of production traffic, with sound instincts for failing open
• Comfort with streaming responses and the parts that get awkward: partial state, mid-stream failures, and work that can only happen once the stream closes
• A strong backend generalist (Python, Kubernetes). We expect you to pick up whatever you have not touched yet
• We weigh trajectory and recent growth more heavily than years of experience

Responsibilities

• Experience at an inference provider or GPU cloud, or contributions to an open-source serving stack
• Fine-tuning and evaluating models in production
• Usage metering, billing, or cost optimization at scale

You.com will only contact you through official @You.com email addresses and will never ask for payment or sensitive personal information during the hiring process.

At You.com, we're thoughtful about how we use AI throughout our business — including our hiring process.

During certain stages of the interview process, we may use AI-powered tools to assist with administrative tasks such as scheduling, note-taking, transcription, or summarizing interview discussions. These tools are intended to support our interviewers by improving accuracy and efficiency — they do not make hiring decisions or replace human judgment.

All employment decisions are made by our recruiting team and hiring managers based on a holistic review of each candidate and applicable evaluation criteria.

If AI-assisted note-taking or transcription may be used during your interview, we will notify you in advance. If you prefer not to participate in an interview that uses these tools, you may opt out by informing your recruiter before your scheduled interview. We will work with you to provide an alternative interview experience where reasonably practicable.

Information collected during the hiring process is handled in accordance with our Privacy Policy and applicable law. By continuing with the application process, you acknowledge that you have read this notice. If AI-assisted tools are used during your interview and you have not opted out after receiving notice, you consent to their use as described above, where permitted by applicable law.