Назад
Company hidden
24 дня назад

Senior Harness Engineer (AI)

Формат работы
remote (только Bulgaria)
Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
Bulgaria
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 govern AI coding agents with an accent on automated quality controls, agent security, and production-grade engineering. Focus on designing feedback sensors, LLM evaluation infrastructure, release gates, observability, and least-privilege controls for autonomous agent workflows.

Location: Remote from Bulgaria

Company

hirify.global is a global analytics software company providing decision-making, credit scoring, fraud detection, and lending solutions.

What you will do

  • Design, build, deploy, and support harness components including guides, feedback loops, guardrails, shared context, and codemods for AI coding agents.
  • Build custom 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 with approaches such as Pact.
  • Operate steering loops, maintain repository knowledge as the system of record, and place controls appropriately across the development lifecycle.
  • Improve observability and metrics for agent-assisted development, partner with product and platform teams, and mentor engineers in harness practices and responsible AI tool use.

Requirements

  • Bachelor's or Master's degree in Computer Science or a related discipline, or relevant commercial experience in software architecture, design, development, and testing.
  • Experience as a seasoned software engineer working with large, complex codebases and a strong foundation in architecture, design, testing, and maintainability.
  • Hands-on experience with AI coding agents such as Claude Code, Codex, or similar tools.
  • Experience building engineering tooling across a modern stack, including linters, static analysis, CI/CD pipelines, containerised build and test environments, and instrumentation or observability; familiarity with AGENTS.md is required.
  • Experience with spec-driven development, context engineering, agent orchestration, fitness functions, and developer-platform work.
  • Ability to encode engineering standards into mechanical, repeatable rules and judge when to use deterministic controls versus LLM-based controls.
  • Experience owning quality-gating processes and defining release criteria.
  • Working knowledge of autonomous-agent security, including prompt injection, tool and permission scoping, sandboxed execution, audit trails, and least-privilege guardrails.
  • Experience with consumer or contract testing approaches such as Pact for distributed service integrations.
  • Excellent communication skills, including the ability to articulate designs with architects and drive standards across teams.

Culture & Benefits

  • Inclusive culture guided by ownership, customer focus, and earning the respect of others.
  • Competitive compensation, benefits, and rewards programs.
  • Professional development through learning experiences and opportunities to leverage individual strengths.
  • People-first work 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 →