Cursor
Software Engineer, Agent Harness
San FranciscofulltimemidAdded 1 month ago
About this role
Join Cursor's Agent Harness team to build core infrastructure powering AI agents across the company's coding automation platform. You'll design agent orchestration, tools, and model behavior systems while defining the default agent experience that millions of users rely on.
What you'll do
- Build and advance the agent harness framework including orchestration, tools, prompts, and execution environments
- Optimize the default Cursor agent experience (Auto model) through intelligent model selection and cost management
- Develop multi-agent coordination capabilities and expand agent platform features
- Integrate new foundational models end-to-end in collaboration with research and external partners
- Design evaluation frameworks and datasets to measure and improve agent performance
- Shape agent personality and behavior based on product requirements and user needs
What they're looking for
- Complex agentic systems and agent infrastructure development
- Production software engineering and systems design
- LLM behavior tuning and model selection strategies
- Evaluation framework and dataset design for AI systems
- Developer tools and platform building experience
- Full-stack implementation and shipping capabilities
- Understanding of emerging AI research and trends
- Cross-functional collaboration with research teams
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Cursor
Cursor builds an AI-driven code editor used by millions of developers to transform how software is built. The company is hiring for infrastructure engineers, ML systems specialists, enterprise platform builders, security engineers, and customer success roles focused on driving adoption within large organizations.
- Website
- cursor.com
Likely interview questions
- Describe a complex agentic system or product you've built. How did you design the agent loop, and what were the key challenges in orchestration?
- Tell us about a time you had to make trade-offs between model capability, cost, and latency in a production system. How did you approach that decision?