> Markdown version of [/jobs/ext/2708341-staff-level-engineer](https://www.wearedevelopers.com/jobs/ext/2708341-staff-level-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # staff-level engineer - **Company:** Tilly - **Location:** United States (Remote available) - **Contract:** Permanent contract - **Skills:** Artificial Intelligence, BigQuery, Code Review, Databases, Software Debugging, Programming Tools, PostgreSQL, Ruby on Rails, Data Streaming, Google Cloud, Heroku, Build Tools, TernJS - **Published:** September 4, 2026 - **Apply:** https://startup.jobs/staff-engineer-rd-ai-tooling-tern-travel-8017742 ## About the Role * Agentic development fluency: Staff or principal background at an AI-native company that has genuinely figured out agentic workflows. Specific things you've shipped, MCP integrations, custom agents, eval frameworks, codegen pipelines, not slides about it. * Public signal: You write or build in the open on agentic patterns, MCP, evals, or codegen. People in this space already follow your work. If we've heard of you and are following your work, we want to talk. * Current individual shipping record: You earn the right to set the bar by being excellent at the work and staying in it. You do not want to step back from shipping. * AI fluency with judgment: You use AI to move dramatically faster while questioning its assumptions. You know when output looks right but isn't, and you build systems that catch it. * Leveling instinct: You're genuinely excited about bringing the team along, not just building ahead of everyone. Navigating that gap, with real excitement about it, is something you've done before. BONUS POINTS * Built developer tooling or internal platforms at scale * Experience with MCP server development or Claude Code integrations * Ruby on Rails background, or shipped in a comparable stack ## Description We're looking for a staff-level engineer who is demonstrably ahead of most teams on agentic development, not in theory, in production. You'll ship real engineering work in the main codebase every week, and from inside that work, build the tooling and workflows that make the entire team faster. The direction you set comes from having your hands on the same problems as the rest of the team. This isn't an architecture role you earn by being right in meetings. The credibility and the tooling both come from being in the work. If you'd rather design from a distance, or build ahead of everyone in isolation rather than teach and pair, this isn't the right fit. If you're the person who has been ahead on agentic workflows for a while and you're hungry to build the team around you into something genuinely exceptional at this, we want to talk. Why Tern? Tern is building the platform travel advisors run their entire business on, and we believe the next great aggregator in travel gets built right now, on AI. The window to win this market is open, and we intend to take it. With capital and real momentum behind us, we're growing the engineering team this summer to put fuel behind what's already working. This role owns a real part of how Tern works, the kind of work the rest of the team depends on. We hire engineers with high agency and the trust to execute independently, set direction through their work, and lift the standard of everyone around them. We hire for proven execution, so we want to see specific evidence of what you've shipped and the impact it had, in your resume and in the room. Engineering Standards 1. Ship regularly. Every engineering pair ships a working, tested feature every week. Fast and good are not in tension. Testing is part of the build. 2. We own our code and how users experience it. We watch what we ship in production, stay close to support, AppSignal, Bugsnag, and Canny, and own our fixes end to end. 3. We make the people around us faster and better, through code and design reviews that teach, through clear written work, and by unblocking our colleagues quickly. 4. Every team is an AI team. We use AI fluently in daily work, from design review to test generation to debugging. We run Claude Code with a deep library of custom skills and agents, unlimited token usage, and we're actively building agentic and MCP-based tooling on top of our own systems. This is how we move fast and build well. Our stack Tern is a Ruby on Rails application with a Hotwire front end, backed by a Postgres database and hosted on Heroku, though we are migrating to Google Cloud Platform. Our data flows through to BigQuery, where we build reporting in Hex. Claude Code, with our own library of custom skills and agents, is part of daily development. You don't need to have used every piece, but you should be fluent enough to be productive quickly and excited to work this way. WHAT YOU'LL DO * Ship real engineering work every week in the same codebase and on the same problems as the rest of the team- your credibility and your tooling both come from being in the work * Accelerate and compound our R&D workflows: optimize day, to, day engineering, build and improve custom skills and agents, push toward fully agentic overnight workflows where they make sense * Tackle the bottlenecks that cap autonomous throughput today, including code review, so more work can run reliably without a human in the loop * Train and certify engineers on new workflows so improvements actually land rather than sitting on a shelf * Treat teaching and building in the open as a primary part of the job, not a tax on it * Level up the team's evals, tooling, and prompt engineering practices from the inside out, * Our interview is built to surface demonstrated execution, and we keep it deliberately light rather than a long gauntlet * We screen resumes for specific, verifiable things you shipped and the impact they had, not responsibilities or titles * We go deep on one or two things you personally built and shipped. We want the real story: the ambiguity, the dead ends, what broke, and how you owned the fix. * We give a practical exercise that reflects the actual work, with AI tools available and expected * And throughout, we look for evidence that working with you made other engineers better at their jobs We take the work seriously, not ourselves. If you're here to grow, build something industry-changing, and raise the bar for the people around you, we'd love to meet you. ## Related Videos - [Agentic employees in world's most downloaded FinTech app](https://www.wearedevelopers.com/videos/100123-agentic-employees-in-world-s-most-downloaded-fintech-app) - [Data Science in Retail](https://www.wearedevelopers.com/videos/586-data-science-in-retail) - [Coffee with Developers - Adam Wiggins](https://www.wearedevelopers.com/videos/919-coffee-with-developers-adam-wiggins) - [Building and Modernising Apps with Agentic AI - Julia Kordick](https://www.wearedevelopers.com/videos/1832-building-and-modernising-apps-with-agentic-ai-julia-kordick) - [Making Data Warehouses fast. A developer's story.](https://www.wearedevelopers.com/videos/302-making-data-warehouses-fast-a-developer-s-story) - [Data Governance in the Era of AI](https://www.wearedevelopers.com/videos/1622-data-governance-in-the-era-of-ai) ## Related Articles - [What is Agentic Programming and Why Should Developers Care?](https://www.wearedevelopers.com/magazine/625-what-is-agentic-programming-and-why-should-developers-care) - [Navigating the AI Shift](https://www.wearedevelopers.com/magazine/629-navigating-the-ai-shift) - [Dev Digest 120 - Apple and peers](https://www.wearedevelopers.com/magazine/455-dev-digest-120-apple-and-peers) - [MLOps And AI Driven Development](https://www.wearedevelopers.com/magazine/82-mlops-and-ai-driven-development) - [Dev Digest 137 - AI'm not sure about this](https://www.wearedevelopers.com/magazine/485-dev-digest-137-ai-m-not-sure-about-this) - [Never delegate the understanding](https://www.wearedevelopers.com/magazine/749-never-delegate-the-understanding)