Назад
Company hidden
6 дней назад

Senior 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
Senior Harness Engineer (AI): Building and operating harness components that guide, verify, and secure AI coding agents with an accent on guardrails, automated feedback loops, and quality gates. Focus on designing LLM evaluation infrastructure, agent security controls, observability, and release criteria for production-grade agent-generated software.

Location: Work from home, United Kingdom

Company

hirify.global is a global analytics software company providing decision-making solutions for businesses in more than 100 countries.

What you will do

  • Design, build, deploy, and support harness components including agent guides, feedback loops, guardrails, shared context, and verification systems.
  • Develop reusable agent instructions, architectural rules, reference documentation, codemods, custom linters, static analysis, and architecture-fitness tests.
  • Define quality gates, release criteria, authority boundaries, and escalation rules for agent-produced work.
  • Build LLM testing and evaluation infrastructure, including AI reviewers and consumer or contract testing such as Pact.
  • Improve agent-work observability and measure cost per merged pull request, merge time, review velocity, defect escape rate, and agent-pull-request survival rate.
  • Partner with product and platform teams, translate 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 equivalent experience in software architecture, design, development, and testing.
  • Strong software engineering experience with large, complex codebases, architecture, design, testing, and maintainability.
  • Hands-on experience with AI coding agents such as Claude Code or Codex, including understanding where they succeed and fail.
  • Experience building engineering tooling across linters, static analysis, CI/CD pipelines, containerized build and test environments, instrumentation, and observability.
  • Experience with spec-driven development, context engineering, agent orchestration, fitness functions, developer platforms, and quality-gating processes.
  • Knowledge of autonomous-agent security, including prompt injection, tool and permission scoping, sandboxed execution, audit trails, and least-privilege guardrails; excellent communication skills are required.

Culture & Benefits

  • Inclusive culture guided by ownership, customer focus, and mutual respect.
  • Professional development through learning experiences and opportunities to use individual strengths.
  • Competitive compensation, benefits, and rewards programs.
  • People-first environment with 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 →