Cursor
Full TimeBuild the inference platform powering every AI interaction at Cursor, optimizing speed, reliability, and cost across multiple model providers at scale. You'll work on the inference gateway, cross-provider failover, routing, and admission control handling millions of requests. This role requires deep experience with high-throughput, low-latency distributed systems—ideally in inference serving, traffic routing, or real-time pipelines—plus comfort reasoning about cost and performance tradeoffs. Based in San Francisco office.
Written from this posting by Neural Jobs AI. The full description is below.
Our mission is to automate coding. The first step in our journey is to build the best tool for professional programmers, using a combination of inventive research, design, and engineering. Our organization is very flat, and our team is small and talent dense. We particularly like people who are truth-seeking, passionate, and creative. We enjoy spirited debate, crazy ideas, and shipping code.
As a Software Engineer on the Model Routing & Inference team at Cursor, you'll build the inference platform that powers every AI interaction in the product.
This team owns the full inference path: making Cursor's AI faster, more reliable, and more cost-effective at a scale few teams in the world get to operate at. Every agent session, every tab completion, and every chat message flows through your stack.
Building and evolving our inference gateway, a single abstraction over every provider's API semantics, so model onboarding becomes a config change.
Designing intelligent cross-provider failover so no single provider outage causes user-visible degradation.
Designing routing backpressure and admission control so traffic spikes don't cascade into providers.
You have deep experience building high-throughput, low-latency distributed systems, especially in inference serving, traffic routing, or real-time data pipelines.
You're comfortable reasoning about cost/performance tradeoffs at scale (GPU utilization, provider economics, capacity planning).
You have strong software engineering fundamentals and enjoy shipping production systems that handle millions of requests.
You make good calls in the gray area: weighing reliability, cost, latency, and user experience when there isn't a single "right" answer.
If there appears to be a fit, we'll reach to schedule 2-3 short technicals. After, we'll schedule an onsite in our office, where you'll work on a small project, discuss ideas, and meet the team.
#LI-DNI
Sign in and we will show how your role, experience, salary and location line up against what this employer asked for.
Check my match
Cursor, developed by Anysphere, is an AI-native code editor that integrates large language models directly into the development workflow, from autocomplete to multi-file edits and agentic coding.
Founded in 2022, it has become one of the most widely adopted AI coding tools.
United States
Search by role, company, or anything a posting mentions.
