Harness Engineer, Director (AI)

Location: Work from Home, United Kingdom

Company

hirify.global is a global analytics software company providing decision-making solutions to businesses in more than 100 countries, including credit scoring, fraud detection, and lending technology.

What you will do

• Lead and contribute hands-on to the design, development, and evolution of an engineering harness for AI coding agents.
• Build agent instruction guides, reusable skills, architectural rules, reference documentation, codemods, feedback sensors, custom linters, and architecture-fitness tests.
• Establish verification loops, LLM-as-judge reviewers, LLM testing infrastructure, AI governance, agent authority boundaries, and quality gates for AI-generated output.
• Define cross-organizational QA and quality standards, determine where controls run across the delivery lifecycle, and prevent recurring agent errors through engineered controls.
• Establish observability and metrics for agent-assisted development, including merge cost, time to merge, review velocity, defect escape rate, and agent-PR survival rate.
• Manage, coach, and grow a geographically distributed team while partnering with engineering leaders and product management on specifications, acceptance criteria, and delivery roadmaps.

Requirements

• Strong software engineering background with experience in large, complex codebases and hands-on expertise in architecture, testing, and maintainability.
• Strong consensus-building and communication skills.
• Hands-on experience with AI coding agents such as Claude Code, Codex, or similar.
• Experience building engineering tooling with linters, static analysis, CI/CD pipelines, containerized build and test environments, instrumentation, observability, and agent instruction conventions such as AGENTS.md.
• Experience with spec-driven development, context engineering, agent orchestration, fitness functions, and developer-platform work.
• Ability to encode quality requirements into mechanical, repeatable rules and judge when to use deterministic controls versus inferential LLM-based controls, including their cost, speed, and reliability trade-offs.
• Demonstrated experience owning AI governance and cross-organizational quality standards, including LLM testing infrastructure and quality gating for AI-generated artifacts.
• Working knowledge of autonomous-agent security, including prompt injection, tool and permission scoping, sandboxed execution, audit trails, and least-privilege guardrails.
• Strong experience managing geographically distributed, high-performing engineering teams and navigating organizational change caused by AI adoption.
• Bachelor’s or Master’s degree in Computer Science or a related discipline, or relevant experience in software architecture, design, development, and testing.

Nice to have

• Ability and interest in evangelizing the harness internally, gathering user feedback, and communicating benefits, tips, and lessons learned.

Culture & Benefits

• Inclusive culture based on ownership, customer focus, and earning the respect of others.
• Professional development through learning experiences and opportunities to use individual strengths.
• Competitive compensation, benefits, and rewards programs.
• People-first work environment supporting work-life balance, employee resource groups, and social events.