Software Engineer, Bugbot

Official role information

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 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 Compensation information {'compensationTierSummary': None, 'scrapeableCompensationSalarySummary': None, 'compensationTiers': [], 'summaryComponents': []}

Review the linked official posting for the complete current wording, application questions and any location-specific terms.

Verified at source level during this run from Cursor's credential-free public Ashby job-board API. The provider returned this record in its current published collection. Missing salary, deadline, visa, funding, eligibility and location facts were not inferred.