Principal Enterprise Data Engineer (AI)

TL;DR

Principal Enterprise Data Engineer (AI): Building and operating harness systems that guide AI coding agents toward reliable, maintainable, production-grade software with an accent on automated verification, quality gates, and agent security. Focus on engineering feedback loops, LLM evaluation infrastructure, architecture controls, and observability for agent-assisted development.

Location: Fully remote from the United Kingdom.

Company

hirify.global is a global analytics software company helping businesses in more than 100 countries make better decisions through analytics, artificial intelligence, machine learning, and optimization.

What you will do

• Design, build, deploy, and support harness components including guides, feedback loops, guardrails, and shared context for AI coding agents.
• Develop linters, static analysis, architecture-fitness tests, verification loops, and LLM-as-judge reviewers.
• Define quality gates, release criteria, authority boundaries, and escalation rules for agent-produced work.
• Establish LLM testing and evaluation infrastructure, including consumer and contract testing for distributed service integrations.
• Improve observability and track agent-development metrics such as merge time, defect escape rate, and cost per merged pull request.
• Partner with product and platform teams, define enforceable controls, and mentor engineers in responsible AI tooling practices.

Requirements

• Relevant degree or commercial experience in software architecture, design, development, and testing.
• Extensive software engineering experience with large, complex codebases and strong architecture, design, testing, and maintainability foundations.
• Hands-on experience with AI coding agents such as Claude Code, Codex, or similar tools.
• Experience building engineering tooling with static analysis, CI/CD pipelines, containerized build and test environments, instrumentation, and observability.
• Knowledge of spec-driven development, context engineering, agent orchestration, fitness functions, developer platforms, and quality-gating processes.
• Understanding of autonomous-agent security, including prompt injection, permission scoping, sandboxed execution, audit trails, and least-privilege guardrails.

Culture & Benefits

• Inclusive, people-first environment built around ownership, customer focus, and mutual respect.
• Professional development through learning experiences and opportunities to use individual strengths.
• Competitive compensation, benefits, and rewards programs.
• Work-life balance, employee resource groups, and social events.