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Software delivery remains trapped in outdated patterns. Backlogs expand without limit, cycle times stretch across weeks, and code review frequently becomes a formality designed to satisfy sprint deadlines. Integration risk, fragile system architectures, and ambiguous requirements plague most development teams. AI coding agents now produce functional code, but only when guided by explicit specifications and monitored with discipline. The industry continues adding developers to projects rather than repairing the underlying process that converts ideas into dependable, production-ready software.

Trilogy has chosen a different approach. We operate an agentic development model from start to finish: engineers lead research, specification design, architectural decisions, and quality oversight, while AI agents execute implementation. Specifications are crafted for execution by Claude Code, following test-first principles and carefully constrained scope to limit risk exposure. This approach enables continuous delivery of production features with substantially faster feedback cycles, reduced integration surprises, and greater confidence in correctness before code reaches the main branch.

This role is for engineers who prefer designing systems and validating correctness over processing task queues. Your time will divide roughly as follows: 10–20% conducting research and technical discovery to map existing behavior, constraints, and stakeholder requirements; 40–50% transforming that knowledge into precise, test-driven, agent-compatible specifications and architectural plans; and 40–50% directing and supervising implementation execution. You own what ships: no silent failures, no vague specifications, no deflecting accountability to the agent.

You'll work with a team that treats specification as engineering output, review as a technical discipline, and delivery as the metric that matters. If you find energy in elegant system architecture, precise scoping, and rigorous validation—and you already integrate tools like Claude Code, Cursor, Copilot, or ChatGPT into your daily practice—this environment will suit you. Bring your architectural expertise, your test-driven development discipline, and your uncompromising standards for code quality. If this describes you, join us and shape the next generation of software delivery. Apply and demonstrate how you direct agents to produce production-grade results at scale.