Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
Зарплата и рынок
ЗП не указанаразвернуть
На похожих ролях по рынку
$73к$82кмедиана$101к
42 в выборке
На СНГ рынке: $4.3к/мес ($3.7к - $5к)
91
Крутая вакансия
развернуть
Это четко описанная senior-роль с ответственностью за AI-инструменты для разработчиков на уровне компании, хотя она объединяет масштабные задачи в платформенной инженерии, тестировании и оценке AI.
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
AI SDLC Engineer - Developer Experience (AI/Developer Tooling): Building platform capabilities and guardrails for agentic software development across evaluation, AI code review, and automated testing with an accent on trustworthy AI-generated code, coverage enforcement, and traceable agent execution. Focus on designing sandboxed agent harnesses, independent quality gates, mutation testing, flaky-test remediation, and measuring developer adoption and trust.
Location: Madrid or Warsaw; hybrid work with working from home up to 40%
Company
hirify.global, through BME, drives the transformation of financial markets and is one of Europe's largest stock exchange groups.
What you will do
Build AI SDLC tooling as a reusable platform covering agent, skill, and prompt evaluation; AI code review in CI; and agent-driven test generation and maintenance.
Develop test-quality capabilities including changed-line coverage enforcement, flaky-test detection and self-healing, mutation testing, and test-suite health analysis across unit, integration, and end-to-end layers.
Build and operate a sandboxed AI agent harness with scoped tools and permissions, CI/CD integration, decision logs, and action provenance.
Own independent review and quality gates for AI-generated code and tests, measuring missed defects, false positives, correctness, coverage, and quality.
Define the quality and tooling strategy for an AI-driven SDLC, including test-data management, regression-detection effectiveness, and enforcement of Enterprise SDLC standards.
Instrument tooling adoption, false-positive rates, and developer trust so the safe, well-tested path remains efficient.
Requirements
Hands-on familiarity with agentic AI architectures, including agent orchestration, tool use, sandboxing, and harness design.
6+ years of software engineering experience, including deep hands-on expertise in developer tooling or platform engineering.
Working knowledge of test methodology and code quality, including test pyramids, coverage strategy, mutation testing, flaky-test remediation, and trustworthy test-suite design.
Platform-product mindset focused on reusable capabilities, developer enablement, adoption, and impact across business units.
Working knowledge of governance and controls in a regulated or high-assurance environment.
Nice to have
Test automation experience.
Experience evaluating LLM or agent systems through evaluation sets, error analysis, and LLM-as-a-judge methods.
Experience building tooling or developer infrastructure adopted by other engineering teams.
Financial market infrastructure experience; adjacent regulated-industry experience is also relevant.
Culture & Benefits
Flexible working models with a balanced and productive work environment.
Continuous learning, feedback, personal development, and broad training opportunities.
Agile working methods including Scrum and design thinking.
Applications are accepted directly only; diversity and inclusion are emphasized.
Hiring process
Only direct applications are accepted.
Questions can be addressed through the FAQ or by contacting Yuliya Stoyko.
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 →