Description
As an embedded software engineer at Cursor, you will work closely with customer teams to design, develop, and deploy production-grade AI-powered systems. Your primary responsibility will be to own an outcome, ship a production-grade SpaceXSI system, and become the critical technical feedback loop from the field back to product engineering.
Responsibilities:
- Lead discovery with customers to identify bottlenecks and define clear success metrics
- Design and ship production agents, AI applications, and coding-agent workflows on Grok and other models
- Get a first version live in days and harden it over weeks with rollout, monitoring, and iteration
- Own production quality, including tracing, evals, debugging, and latency and cost tradeoffs
- Build systems around the model and integrate them into customer systems
- Measure outcomes that matter, such as revenue, cost, hours saved, error rate, cycle time, and escaped defects
- Work directly with staff, platform, and domain leaders
- Leave the customer team able to run what you built and turn what you learn into reusable patterns and improvements to SpaceXSI products
Requirements:
- 5+ years of experience in software engineering, machine learning engineering, or data science
- Proficiency in languages such as Python, JavaScript/TypeScript
- Experience owning customer or operator outcomes and turning fuzzy problems into scoped, shipped systems
- Experience building and owning AI-native workflows or agents in production and debugging real production failures
- Experience handling production reliability, including metrics, alerts, safe rollouts, and incident response
- Ability to build end-to-end systems, including frontend, backend, infra, and prompt iteration
- Comfort working in ambiguity and communicating with working engineers and VPs
Nice to Have:
- 2+ years of experience in a customer-facing role, leading discovery conversations and being accountable for outcomes
- Hands-on depth in areas such as agents and tool-calling, eval harnesses, retrieval and context systems, CI/CD or developer platforms, and AI-native coding workflows
- Experience as a forward-deployed, solutions, or platform engineer embedded with customers, or as a founding engineer who owned an AI product end to end