AI Software Engineer - Internship

Role Overview

You will work as an AI Software Engineer Intern in a 100% remote role (must be based in the United States). The position combines four roles into one: product/requirements writer, AI-assisted builder, QA tester, and documentation engineer.

What You’ll Do

• Documentation & Requirements (Claude Desktop):
  • Convert existing epic overview documents into detailed, unambiguous requirements (user stories, acceptance criteria, flows, states, edge cases, validation rules).
  • Keep documentation clear, consistent, and current as features evolve.
  • Identify gaps, missing flows, and open questions before implementation.
• Build with AI (Claude Code / Claude CLI):
  • Build features by directing Claude Code / Claude CLI, decomposing work and prompting with the right context.
  • Integrate and ship working software end-to-end across the stack.
  • Maintain a clean, conventional, maintainable codebase.
• QA & Testing (Claude Code):
  • Write and run tests using Claude Code, and QA your own work against the acceptance criteria you created.
  • Review AI-generated code by reading diffs, spotting bugs, and verifying behavior.
  • Document what you tested and how.

Requirements

• Master’s degree in Software Engineering, Computer Science, HCI, or a closely related field.
• Must be based in the United States.
• Hands-on experience with Anthropic Claude tools:
  • Claude Desktop (documentation/requirements)
  • Claude Code / Claude CLI (building/QA)
  • Ability to demonstrate real usage (e.g., documenting/building/shipping something).
• Strong written communication to turn ambiguity into structured requirements.
• Ability to critically review code to catch bugs in AI-generated output.
• Comfort owning a feature end-to-end: spec → build → test → document.

Nice to Have

• Experience with Laravel, React, or Tailwind CSS.
• Product, business-analysis, or QA experience.
• Portfolio/side project/repo built with AI coding tools.
• Experience with multi-tenant SaaS products.

How We Work

Spec-driven and AI-first: write requirements clearly, let AI build to them, then verify through disciplined review and testing.