About this role
SpaceX was founded under the belief that a future where humanity is out exploring the stars is fundamentally more exciting than one where we are not. Today, SpaceX is actively developing the technologies to make this possible, with the ultimate goal of making life multiplanetary and expanding consciousness to the stars. SpaceXSI is building Super Intelligence to help humanity understand the universe. Our teams are building the full Super Intelligence stack: from our Colossus supercomputers, to Grok models, to our suite of applications, including Grok Bot, Grok Build, Grok Imagine, Grok Voice, and X. We're creating a powerful flywheel where more compute trains better models, better models power more useful products, and what we learn from people using those products shapes what we build next. About the role We're hiring a Software Engineer to work on Bugbot. Bugbot reviews pull requests, catches bugs, suggests improvements, and is becoming a critical part of how engineering teams ship software. As LLMs rapidly mature, the surface area of what Bugbot can do is expanding just as fast. From the model integration and agent harness improvement to the product UI, integrations, and onboarding experience, you’ll maintain Bugbot being the industry's best AI code reviewer. This is a full-stack IC role where you'll ship features end-to-end and directly shape how millions of engineers interact with AI during code review. What you’ll do - Launch new Bugbot features end-to-end from defining the feature and building the UI to wiring up the backend and iterating on model behavior so that each release meaningfully improves code review quality. You can check out Bugbot blog post for some examples of how Bugbot was improved in the past: https://cursor.com/blog/building-bugbot . - Evolve the review pipeline adapting prompting strategies, model routing, context selection, and agent orchestration to take advantage of new capabilities while managing cost and latency. - Build integrations that embed Bugbot into every engineer's workflow making AI-assisted review a seamless, default part of the development loop. - Own product quality and reliability monitor precision and recall, triage false positives, improve observability across the review pipeline, and ensure Bugbot earns trust with every review it posts. - Design onboarding and adoption flows that help teams go from first install to daily active usage. - Partner with ML, infrastructure, and product teams to inform model improvements with real-world review data, shape the Bugbot roadmap, and scale the system as adoption grows. - You will own Bugbot's product surface end-to-end: features, integrations, review pipeline, onboarding, configuration, and the user experience of AI code review. - You will not own foundation model training or core infrastructure services — but you will be a key consumer and collaborator, driving requirements based on what Bugbot needs. - You will not be a backend-only engineer or an ML researcher who doesn't ship product. This role requires you to move fluidly between the model layer and the product layer. - Quality is the product. A code review assistant that posts noisy or unhelpful comments is worse than no assistant at all. You'll be obsessive about making Bugbot's output genuinely useful. You obsess about your evals. You may be a fit if - You’ve built or worked on agents that integrate into the code review or CI/CD workflow. - You’ve shipped full-stack product features end-to-end and enjoy moving between frontend, backend, and model integration. - You care deeply about developer experience and collecting new evals from customers and internal team members. - You can hold the tension between "ship fast to learn" and "don't erode trust with bad suggestions." - You’ve launched a product or feature to external users and owned the full loop: onboarding, documentation, feedback, and iteration. #LI-DNI