Software Engineer, Model Routing & Inference
Cursor·New York, New York, United States | San Francisco, California, United States·posted 131d ago · last seen 46m agoTrack this application
Get Started FreeMatch score against your CV
Get Started FreeTailor your resume to this job
Get Started FreeAbout interviewing at Cursor
Short and fast: a recruiter screen, then '2-3 short technicals' (Cursor's own job-posting wording), then the signature round — an onsite in their office where you build a real project. CEO Michael Truell has said every engineering and design hire spends two days in-office working on a project: you get a desk, a laptop, a choice of three projects, and a frozen older copy of the real codebase with the dev environment set up, then present what you built. Crucially, first technical screens BAN AI beyond autocomplete ('programming without AI is still a really great time-boxed test for skill and intelligence' — Truell), while the onsite expects you to work with full tooling including Cursor itself. There is no formal behavioral round — the 4-6 meals with the team during the trial are the culture interview. Decisions come fast; the whole loop targets weeks, not months.
Read the full Cursor interview process →Description
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.
About the Role
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.
Example projects include...
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 may be a fit if
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.
Applying
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
More engineering roles at Cursor
Product Education Engineer
RVP, Forward Deployed Engineering - EMEA
Forward Deployed Engineer
Full Stack Analyst, GTM