Мы используем технические cookie и статистику посещений: Яндекс Метрику и собственный обезличенный журнал Zorky (cookie zk_aid). Не собираем содержимое форм, текст поиска и полный IP; данные не продаём. Отказаться можно кнопкой ниже, а также через Global Privacy Control или Do Not Track в браузере. Подробнее о cookie и статистике.
Zorky CRMZorky CRM
EN|RU
@termdocs
← Все вакансии

Senior QA / ML Tester

seniorremote2,000 USD · период не указанKatowice, PLСкор 78/1002нед назад
Аналитика рынка
📊 QA / Testing: зарплаты и спрос на рынке
Стек
PythonpytestLLM Evaluationintegration testingAWS AgentCoreOpenTelemetryREST API TestingJiraagileawsazureci/cd
Откликнуться
Загрузите резюме — мы свяжем вас с работодателем напрямую через нашу базу.
Отправить резюме →
Описание
We are looking for a Senior QA / ML Tester to join the AI Platform team and take ownership of quality assurance for the Agent Evaluation Framework built on AWS AgentCore. This role involves designing, implementing, and maintaining a functional test suite that validates the correctness of AI agent evaluation pipelines — covering on-demand integration testing, online sampling accuracy, and multi-evaluator execution — and delivering a feasibility assessment for non-AgentCore runtime evaluation scenarios. This is a hands-on, production-focused role at the intersection of software quality engineering and AI/ML system testing, operating within an Agile delivery team and contributing to the reliability of enterprise-grade agentic AI infrastructure. Responsibilities Design and implement a functional test suite for the AWS AgentCore Evaluation API using pytest, covering known-good / known-bad session pair validation, multi-evaluator execution correctness, and edge case handling Develop and maintain integration tests for on-demand evaluation mode, integrated into the CI/CD pipeline with automated execution on each build Validate online mode sampling accuracy, design test scenarios, define acceptance criteria, and report deviations with reproducible evidence Conduct and document a feasibility assessment for non-AgentCore runtime evaluation: analyze alternative runtimes, define evaluation methodology, and deliver a structured findings report Test OpenTelemetry trace-based evaluation inpu
Контакты работодателя (email/phone/telegram) скрыты из публичного превью — отправьте резюме, чтобы мы связали вас напрямую.
Срочный вопрос? Напишите @termdocs