Назад
Company hidden
4 дня назад

Principal Harness Engineer (AI)

Формат работы
remote (только United_kingdom)
Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
UK
Вакансия из списка Hirify.GlobalВакансия из Hirify Global, списка международных tech-компаний
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/
TL;DR
Principal Harness Engineer (AI): Building the guides, feedback loops, guardrails, testing infrastructure, and observability that steer AI coding agents toward production-grade engineering with an accent on automated verification, quality gating, and agent security. Focus on designing deterministic and LLM-based controls, defining release criteria, and preventing recurring agent failures through enforceable engineering systems.

Location: Work from Home, United Kingdom

Company

hirify.global is a global analytics software company that helps 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 the guides, feedback loops, guardrails, and shared context that form the harness for AI coding agents.
  • Develop agent instruction files, reusable skills, architectural rules, reference documentation, and codemods, driving engineering standards across teams.
  • Build custom linters, static analysis, architecture-fitness tests, verification loops, and LLM-based review systems to identify issues before human review.
  • Define quality gates, release criteria, agent authority boundaries, and escalation rules for agent-produced work.
  • Establish LLM testing and evaluation infrastructure, apply consumer and contract testing, and improve observability of agent-assisted development.
  • Partner with product and platform teams, convert specifications into enforceable controls, and mentor engineers in harness practices and responsible AI tool usage.

Requirements

  • Bachelor's or Master's degree in Computer Science or a related discipline, or relevant commercial experience.
  • Strong experience in software architecture, design, development, and testing across large, complex codebases.
  • Hands-on experience with AI coding agents such as Claude Code, Codex, or similar tools.
  • Experience building engineering tooling with linters, static analysis, CI/CD pipelines, containerized build and test environments, and observability.
  • Knowledge of spec-driven development, context engineering, agent orchestration, fitness functions, and developer-platform work.
  • Working knowledge of autonomous-agent security, including prompt injection, permission scoping, sandboxed execution, audit trails, and least-privilege guardrails; excellent communication skills are required.

Nice to have

  • Experience with consumer or contract testing approaches such as Pact.
  • Familiarity with agent instruction conventions such as AGENTS.md.

Culture & Benefits

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

Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →