Staff Software Engineer, Delivery Engineering

About CircleCI Engineering CI/CD has been solved. Now it's being reinvented. AI agents don't just run pipelines. They write code, trigger builds, interpret failures, and propose fixes. The interfaces that developers use to understand and trust that work don't exist yet. We're building them. At CircleCI, our guiding principles aren't posters on a wall. We learn fast: we run experiments, accept failure, and scale what works. We think like the customer: every decision connects back to the developer sitting in front of a failing build at 2 am. We own the outcome: not just our slice of it, but the whole thing. If that's how you already work, you'll fit here. About Delivery Engineering Delivery Engineering enables CircleCI engineers to deliver quickly, confidently, and securely. We provide the tools and resources that make standard patterns and best practices simple to adopt, and we reduce toil. Our current focus is the agentic software development lifecycle: how changes are found, planned, built, reviewed, merged, and measured as AI agents take on more of the work. We evaluate the harnesses, repository patterns, skills, and agentic tooling available, decide what our teams should standardize on, and build and support the shared tooling other teams depend on. We're a small, very senior team, and everyone on it shapes where we go. Every improvement we make compounds across the organization. What You'll Do - Build AI-natively. AI is how we work. It's not a productivity layer on top of engineering, but the default starting point for how problems get approached and solved. - Shape how CircleCI builds software with agents. Help define the end-to-end agentic SDLC, from identifying a change through planning, execution, pull request, merge, and measuring impact afterward. Evaluate shared tooling and patterns, and help decide what teams standardize on. - Start from how our teams actually work. Spend time with engineering teams to understand their workflows and where they get stuck. Use what you learn to drive decisions and direction that teams adopt because the work fits how they operate.

- Build platforms, not one-offs. Build and support shared tooling that other teams depend on, and own its adoption as much as its delivery. A tool nobody uses isn't done. - Measure what matters. Instrument agent usage and outcomes so we know what improves throughput and quality and what just burns tokens. Treat cost, model choice, and reliability as design concerns. - Make build-vs-buy calls. Evaluate models, vendors, and open-source tools against our needs, and choose the path that gets engineers the most leverage. - Lead through influence. Write the design docs, lead technical discussions across teams, and mentor engineers across the org as they adopt agentic workflows. What You'll Bring - Direct experience driving agentic developer experience efforts. You've driven an initiative that changed how an engineering organization builds software with AI agents. You can speak to what you built, how you measured its impact, how you drove adoption, and what didn't work. - Hands-on depth with agentic tooling. You work daily with coding agents, agent harnesses, MCP, and skills or prompt design. You know how to evaluate agent output and reason about model and token economics. - A platform mindset. You've built and supported internal platforms or developer tooling that other engineers build on and rely on, and driven their adoption. - Backend depth in Go. You've owned production backend services in Go, including API design, data modeling, and service integration. - A track record at staff scope. 8+ years of production engineering experience, including technical decisions that spanned multiple teams and accountability for whether they landed. - Decision-making grounded in your users. You build direction by listening first. You turn the needs of many teams into clear tradeoffs, document your reasoning, and bring people along.