Senior Harness Engineer

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

📋 Description

• Design, develop, deploy, and maintain essential harness components, which include guides, feedback loops, guardrails, and shared context.

• Take ownership of and enhance agent instruction files, reusable skills, architectural standards, reference documentation, and codemods.

• Create custom linters, perform static analysis, conduct architecture-fitness tests, establish verification loops, and implement LLM-as-judge reviews.

• Manage quality gating and release criteria for agent-generated outputs, encompassing authority boundaries and escalation protocols.

• Set up LLM testing frameworks and evaluation methods for AI-generated content.

• Implement consumer/contract testing in scenarios where service integration reliability is critical.

• Conduct steering loops to avoid repetitive agent errors and maintain repository knowledge as the definitive source of truth.

• Determine the placement of controls throughout the production pathway, from pre-commit checks to continuous drift monitoring.

• Enhance visibility into agent activities and track performance metrics related to engineering and agent-PR outputs.

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

• Provide technical guidance and mentorship to engineers across teams regarding harness practices and the responsible use of AI tools.

⛳️ Requirements

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

• Experienced software engineer with a robust background in handling large, complex codebases and a solid understanding of architecture and design principles.

• Strong dedication to testing and maintainability.

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

• Capability to develop engineering tools across contemporary stacks, including linters, static analysis, CI/CD pipelines, containerized build/test environments, and instrumentation/observability.

• Familiarity with agent instruction conventions like AGENTS.md.

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

• Systems-oriented mindset with the ability to translate quality standards into mechanical, repeatable processes.

• Sound judgment regarding deterministic computational controls versus inferential LLM-based controls, including considerations of cost, speed, and reliability trade-offs.

• Experience in managing quality-gating procedures and establishing release criteria.

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

• Proficiency in consumer/contract testing methodologies such as Pact.

• Outstanding communication abilities, with the capacity to articulate designs to architects and promote standards across teams.

🏝️ Benefits

• An inclusive culture that embodies FICO's core values.

• Opportunities for professional development and valuable learning experiences.

• Competitive compensation, comprehensive benefits, and rewarding programs.

• Emphasis on work/life balance.

• Access to employee resource groups.

• Engaging social events.

• A diverse and inclusive workplace environment.

• Support for skill development and career growth.