Software delivery remains trapped in outdated rhythms. Backlogs accumulate, cycle times stretch across weeks, and "code review" frequently devolves into a formality to meet sprint deadlines. Most engineering organizations struggle with integration hazards, fragile system architectures, and poorly defined requirements. At the same time, AI coding agents demonstrate the capacity to produce viable code—but only when given explicit specifications and maintained under close supervision. The industry continues to add more developers to the problem rather than repairing the underlying system that transforms intention into dependable, production-ready software.
Trilogy has chosen a fundamentally different approach. We operate an agent-driven development pipeline from beginning to end: engineers own research, specification, architecture, and quality control, while AI agents execute the implementation. Specifications are crafted to be directly executable by Claude Code, test-first in design and narrowly scoped to reduce impact radius. The outcome is continuous deployment of production features with significantly shorter feedback cycles, reduced integration surprises, and elevated confidence in correctness before code reaches the main branch.
This position is designed for engineers who prefer designing systems and verifying correctness over cycling through tickets. You will allocate approximately 10–20% of your time to research and technical discovery—understanding current behavior, constraints, and stakeholder requirements; 40–50% translating that knowledge into precise, test-driven, agent-executable specifications and architectural choices; and 40–50% orchestrating and overseeing implementation. You own what gets deployed: no silent breakages, no vague specifications, no deflecting responsibility to "the agent."
You will work with a team that views specification as a deliverable, review as an engineering practice, and delivery as the singular metric that matters. If you are motivated by clean system design, precise scoping, and rigorous validation—and you already incorporate tools like Claude Code, Cursor, Copilot, or ChatGPT into your everyday workflow—this environment will suit you well. Bring your architectural expertise, your test-driven development principles, and your uncompromising standards for code quality. If this resonates with you, join us and shape the future of how software is created. Apply and demonstrate how you direct agents to produce production-grade results at scale.
Crossover's skill assessment process combines innovative AI power with decades of human research, to take the guesswork, human bias, and pointless filters out of recruiting high-performing teams.






It’s super hard to qualify—extreme quality standards ensure every single team member is at the top of their game.
Over 50% of new hires double or triple their previous pay. Why? Because that’s what the best person in the world is worth.
We don’t care where you went to school, what color your hair is, or whether we can pronounce your name. Just prove you’ve got the skills.
Join the world's largest community of AI-first remote workers.