AI Software Engineer

$100,000 USD/year ^{Pay is set based on global value, not the local market. Most roles = hourly rate x 40 hrs x 50 weeks}  ($50 USD/hour)

Software delivery remains trapped in legacy workflows. Backlogs expand endlessly, cycle times stretch across weeks, and code reviews frequently devolve into formalities designed to meet sprint deadlines. Many engineering organizations struggle with integration fragility, unstable architectures, and requirements that lack clarity. At the same time, AI coding agents demonstrate the capacity to produce functional code—but only when provided with rigorous specifications and close oversight. The prevailing response has been to add more developers rather than redesign the system that transforms intent into dependable, production-ready software.

Trilogy has chosen a different approach. We operate an end-to-end agentic development model: engineers own research, specification, architecture, and quality control, while AI agents execute implementation. Specifications are crafted to be machine-executable by Claude Code, following test-first principles and scoped with surgical precision to contain risk. This process enables continuous delivery of production features, tighter feedback cycles, reduced integration uncertainty, and greater confidence in correctness before code reaches the main branch.

This role is designed for engineers who prefer system design and correctness validation over ticket processing. You will allocate approximately 10–20% of your time to research and technical discovery—understanding existing behavior, constraints, and stakeholder expectations. Another 40–50% will go toward translating that understanding into precise, test-driven, agent-executable specifications and architectural guidance. The remaining 40–50% will be spent orchestrating and supervising implementation. You own what ships: no silent breakages, no vague specifications, no deflecting responsibility to the agent.

You will be part of a team that treats specification as engineering output, code review as a technical discipline, and delivery as the metric that matters. If you are motivated by refined system design, deliberate scoping, and rigorous validation—and you already integrate tools like Claude Code, Cursor, Copilot, or ChatGPT into your daily work—this environment will suit you. Bring your architectural judgment, your test-driven instincts, and your high standards for code quality. If this aligns with your strengths, step forward and help define the next generation of software development. Apply and demonstrate how you orchestrate agents to deliver production-grade results at scale.