Senior/Lead AI Harness Engineer

About the role

A hands-on technical role building the environment that steers AI coding agents toward correct, maintainable output, so quality is enforced by systems rather than re-checked by people on every change.

What you will do

• Build feedback sensors including custom linters, static analysis, architecture fitness tests, verification loops and LLM judge reviewers
• Engineer controls so repeated agent mistakes cannot recur, and keep repository knowledge legible to agents
• Contribute to quality gating, release criteria and LLM testing for quality and safety thresholds
• Improve observability into agent work and track metrics such as cost per merged PR and defect escape rate

What they look for

• Bachelor's or master's in computer science or a related field, or equivalent experience in software architecture, design, development and te
• Strong software engineering background with large codebases and care for architecture, testing and maintainability
• Comfort building tooling across linters, static analysis, CI pipelines, containerized build and test environments, and observability
• Hands-on experience with AI coding agents such as Claude Code or Codex, and a sense of where they succeed and fail
• A systems mindset and the ability to encode quality expectations into mechanical, repeatable rules