Principal Harness Engineer

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

📋 Description

• Design, develop, deploy, and support key harness components, such as guides, feedback loops, guardrails, and shared context.

• Take ownership of and enhance feedforward guides, agent instruction files, reusable skills, architectural rules, reference documents, and codemods.

• Drive standardization across the team for AI-agent outputs.

• Create feedback sensors, including custom linters, static analysis tools, architecture fitness tests, verification loops, and LLM-as-judge reviewers.

• Oversee quality gating and release criteria for work produced by agents.

• Define authority boundaries for unaided agent merges and establish escalation protocols for human review.

• Set up LLM testing infrastructure and evaluation methods for AI-generated outputs.

• Implement consumer/contract testing where the reliability of service integration is crucial.

• Manage the steering loop to avoid repetitive agent errors and maintain repository knowledge.

• Determine the locations where controls operate along the production path.

• Enhance observability of agent tasks and monitor metrics such as cost per merged PR, time-to-merge, review velocity, defect escape rate, and agent-PR survival rate.

• Collaborate with product and platform teams to translate specifications and acceptance criteria into enforceable controls.

• Act as a technical expert and mentor engineers in harness practices and the responsible use of AI tools.

⛳️ Requirements

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

• Proven experience as a seasoned software engineer with large, complex codebases.

• Strong foundation in software architecture and design principles.

• Hands-on experience with AI coding agents like Claude Code, Codex, or similar technologies.

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

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

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

• Ability to translate quality standards into mechanical, repeatable rules.

• Sound judgement in assessing deterministic computational controls versus inferential LLM-based controls, including considerations for cost, speed, and reliability trade-offs.

• Experience managing quality-gating processes and defining release criteria.

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

• Familiarity with consumer/contract testing strategies such as Pact.

• Excellent communication skills and the ability to articulate designs with architects while promoting standards across teams.

🏝️ Benefits

• Highly competitive compensation, benefits, and rewards programs.

• Work/life balance.

• Employee resource groups.

• Social events.

• Valuable learning experiences.

• Professional development opportunities.

• Inclusive, people-first workplace environment.