Harness Engineer, Director

This is a fully remote position, open to applicants in United Kingdom.

📋 Description

• Lead a new internal Harness Engineering team dedicated to ensuring AI coding agents operate effectively at scale.

• Design, construct, and enhance harness components, guidelines, feedback mechanisms, guardrails, and shared context.

• Create and sustain agent instruction files, reusable skills, architectural regulations, reference materials, and codemods.

• Develop feedback sensors, custom linters, architecture-fitness assessments, verification loops, and LLM-as-judge reviewers.

• Oversee regional AI governance, encompassing agent authority boundaries, LLM testing infrastructure, as well as quality, safety, and compliance standards.

• Define and take ownership of cross-organizational QA and quality-gating protocols.

• Conduct steering loops to avert recurring agent errors and maintain repository knowledge as the authoritative system of record.

• Determine the placement of controls throughout the production process.

• Establish observability into agent operations and monitor engineering quality and delivery metrics.

• Manage, mentor, and develop a geographically distributed team of harness engineers.

• Collaborate with engineering leaders and product management to align harness controls with specifications and delivery roadmaps.

• Provide internal enablement, presentations, and thought leadership on agent-augmented engineering.

⛳️ Requirements

• Solid software engineering foundation with experience in large, intricate codebases.

• Practical experience with AI coding agents such as Claude Code, Codex, or similar technologies.

• Background in developing engineering tools across a contemporary stack.

• Familiarity with linters and static analysis, CI/CD pipelines, containerized build/test environments, instrumentation, and observability.

• Knowledge of agent instruction conventions like AGENTS.md.

• Experience with specification-driven development, context engineering, agent orchestration, fitness functions, and developer-platform initiatives.

• Proven experience in managing AI governance and cross-organizational quality standards.

• Experience in establishing LLM testing infrastructure and quality gating for AI-generated outputs.

• Understanding of autonomous-agent security, prompt injection, tool/permission scoping, sandboxed execution, and audit trails.

• Extensive experience leading geographically distributed, high-performing engineering teams.

• Outstanding communication and consensus-building abilities.

• Bachelor's/Master's degree in Computer Science or a related field, or equivalent experience in software architecture, design, development, and testing.

• Willingness or interest in promoting initiatives internally and collecting user feedback.

🏝️ Benefits

• Highly competitive compensation, benefits, and rewards programs.

• Work/life balance.

• Employee resource groups.

• Social events.

• Learning experiences and professional development opportunities.

• Inclusive, people-first work environment.