Software delivery remains trapped in outdated practices. Backlogs expand endlessly, cycle times stretch into weeks, and "code review" often devolves into perfunctory approval to meet sprint deadlines. Most engineering organizations struggle with integration failures, fragile system designs, and ambiguous requirements. At the same time, AI coding agents demonstrate the ability to produce viable code—but only when provided with rigorous specifications and close supervision. The prevailing response continues to be adding more developers rather than fundamentally improving the system that transforms requirements into dependable, production-ready software.
Trilogy has chosen a fundamentally different approach. We operate an agentic development pipeline from start to finish: engineers own research, specification, architecture, and quality control, while AI agents execute implementation. Specifications are crafted to be directly executable by Claude Code, following test-first principles and carefully scoped to contain impact radius. The outcome is continuous deployment of production functionality with significantly faster feedback cycles, reduced integration surprises, and greater confidence in correctness before any code reaches the main branch.
This position is designed for engineers who want to architect systems and validate correctness rather than process tickets. You will allocate approximately 10–20% of your time to research and technical investigation—understanding current system behavior, constraints, and stakeholder requirements; 40–50% translating that knowledge into precise, test-driven, agent-executable specifications and architectural choices; and 40–50% directing and supervising implementation execution. You own accountability for shipped results: no silent errors, no vague specifications, no deflection to "the agent's output."
You will become part of a team that treats specification as a deliverable product, review as an engineering practice, and delivery as the singular metric that matters. If you find energy in refined system architecture, precise scoping, and rigorous validation—and you already integrate tools like Claude Code, Cursor, Copilot, or ChatGPT into your daily engineering practice—you will excel in this environment. Bring your architectural expertise, your test-driven development discipline, and your uncompromising standards for code quality. If this resonates with you, step forward and shape the future of software construction. Apply and demonstrate how you direct agents to deliver production-quality 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.