Director – Harness Engineering

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

📋 Description

• Personally design, construct, and enhance the harness for AI coding agents.

• Develop and sustain feedforward guides, reusable skills, architectural guidelines, reference documentation, and code modifications.

• Create feedback mechanisms including custom linters, structural and architectural fitness tests, verification loops, and LLM-as-judge evaluators.

• Oversee regional AI governance, establish authority boundaries, and maintain LLM testing infrastructure as well as quality, safety, and compliance benchmarks.

• Define and manage cross-organizational quality assurance and quality-gating standards.

• Execute the steering loop to engineer controls that mitigate recurring agent errors.

• Manage repository knowledge as the system of record, actively combating knowledge drift.

• Determine the placement of controls throughout the production path, from pre-commit checks to post-integration and continuous monitoring.

• Establish observability into agent activities and track metrics such as cost per merged pull request, time-to-merge, review velocity, defect escape rate, and agent-pull request survival rate.

• Lead, mentor, and develop a geographically dispersed team of harness engineers.

• Collaborate with stakeholders to attract talent, set objectives, and assess and reward performance.

• Work together with engineering leaders and product management to convert specifications and acceptance criteria into enforceable controls.

• Align the harness with platform and delivery roadmaps.

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

⛳️ Requirements

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

• Strong background in software engineering, particularly with large, complex codebases.

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

• Experience in developing engineering tools across modern technology stacks, including linters, static analysis, CI/CD pipelines, containerized build and test environments, and instrumentation/observability.

• Familiarity with agent instruction conventions such as AGENTS.md.

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

• Ability to encode quality standards into mechanical, repeatable processes.

• Judgment in determining when to apply deterministic computational controls versus inferential LLM-based controls.

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

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

• Working knowledge of autonomous-agent security, including prompt injection, tool and permission scoping, sandboxed execution, and audit trails.

• Significant experience managing high-performing engineering teams across geographical locations.

• Experience in navigating organizational change associated with AI adoption.

• Excellent communication abilities.

🏝️ Benefits

• Highly competitive compensation, benefits, and rewards programs.

• Work/life balance.

• Employee resource groups.

• Social events to foster interaction and camaraderie.

• Valuable learning opportunities.

• Professional development prospects.

• An inclusive, people-first work environment.