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 

Not accepting applications on crossover.com at this time.

Description

Software delivery remains trapped in outdated patterns. Backlogs pile up, delivery timelines stretch into weeks, and code review often degrades into a formality designed to meet sprint deadlines. Teams struggle with integration failures, fragile system architectures, and ambiguous requirements. At the same time, AI coding agents demonstrate the ability to produce functional code—but only when guided by precise specifications and rigorous oversight. The industry continues adding more developers to keyboards rather than addressing the underlying system that converts intention 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 directly executable by Claude Code, following test-first principles and narrowly scoped to reduce integration risk. The outcome is continuous deployment of production features with significantly faster feedback cycles, reduced integration surprises, and greater confidence in correctness before code reaches the main branch.

This role is designed for the engineer who prefers designing systems and validating correctness over processing tickets. You will allocate approximately 10–20% of your time to research and technical discovery—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% coordinating and supervising implementation execution. You own accountability for what deploys: no silent breakages, no vague specifications, no deflection to "the agent did it."

You will become part of a team that views specification as a deliverable product, review as an engineering practice, and delivery as the ultimate performance metric. 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 everyday workflow—this environment will suit you. Bring your architectural expertise, your test-driven development instincts, and your uncompromising standards for code quality. If this resonates with you, step forward and shape the future of how software is constructed. Apply and demonstrate how you orchestrate agents to deliver production-grade results at scale.

What you will be doing

  • Technical Discovery: Examining existing systems, stakeholder needs, and data sources to map the problem domain and identify technical constraints
  • Technical Specification: Transforming research insights and stakeholder inputs into precise, executable technical specifications tailored for agentic coding assistants (primarily Claude Code) using spec-driven development methodology
  • AI Implementation: Directing AI coding agents to execute specifications, performing continuous review and validation of agent-generated code, and merging validated changes into the production codebase

Key responsibilities

  • Continuous delivery of production-quality software features and systems through agentic development workflows, in which AI coding agents execute implementation while engineers control specification, architecture, and quality assurance

Candidate requirements

  • Minimum 3 years of professional software engineering experience in production environments
  • Experience engaging in pull request review processes
  • Experience working with AI coding tools (e.g. Claude Code, Windsurf, Cursor) in a professional setting

Meet a successful candidate

Watch Interview
Fabiano Lucchese
Fabiano  |  SVP of Software Engineering
Brazil  

Does your company encourage your natural creativity? This Brazilian engineering leader rediscovered his purpose after unleashing both his an...

Meet Fabiano

Applying for a role? Here’s what to expect.

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.

Chat-style
screening interview.
STEP 1

Chat-style
screening interview.

Cognitive 
aptitude test.
STEP 2

Cognitive 
aptitude test.

Prove real-world 
job skills.
STEP 3

Prove real-world 
job skills.

Interview with the hiring manager.
STEP 4

Interview with the hiring manager.

Pass
proctored test.
STEP 5

Pass
proctored test.

Accept job offer.
STEP 6

Accept job offer.

Frequently asked questions

About Crossover

Meet some people who've landed similar jobs

Why Crossover

Recruitment sucks. So we’re fixing it.

The Olympics of work

The Olympics of work

It’s super hard to qualify—extreme quality standards ensure every single team member is at the top of their game.

Premium pay for premium talent

Premium pay for premium talent

Over 50% of new hires double or triple their previous pay. Why? Because that’s what the best person in the world is worth.

Shortlist by skills, not bias

Shortlist by skills, not bias

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.

Crossover Logo White
Follow us on
Have a question?

Get answers to common questions using our smart chatbot Crosby.

HELP AND FAQs

Join the world's largest community of AI first Remote WorkersAI-first remote workers.