Software Engineer, Agent Harness
Cursor·New York, New York, United States | San Francisco, California, United States·posted 292d ago · last seen 51m 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 Agent Harness team at Cursor, you’ll build the core agent behavior and capabilities that power agent experiences across Cursor products. This spans agent orchestration, tools, guardrails, and model behavior tuning—designed as a platform that Cursor engineers can extend and depend on.
Your work will also define the default Cursor agent experience (”Auto”), where users trust us to make the right model choices under real-world constraints.
Example projects include:
Advancing the agent harness (agent loop, tools, prompts, execution environment, capabilities) used across Cursor products. This would shape and empower experiences like multi-agent coordination.
Improving the default Cursor agent experience (the “Auto” model setting): making smart model choices based on user needs, model capabilities, and cost appetite.
Shaping the default Cursor agent’s personality.
Launching new models on Cursor end-to-end — partnering with foundational model providers and our research team on integration, evaluation, and rollout.
You may be a fit if
You have built complex agentic products or infrastructure.
You have strong software engineering fundamentals and enjoy shipping production systems.
You have taste and strong opinions on model and agent behaviors. You stay up-to-date and informed on emerging research and industry trends.
You make good calls in the gray area: weighing data, user experience, and product taste when there isn’t a single “right” answer.
Experience building eval datasets or frameworks to understand and improve the performance of AI systems is a plus.
Experience building products or tools used by other engineers is a plus.
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