aipythonkubernetesfastapidockertypescriptawsragci cdagentic ai
Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
Зарплата и рынок
ЗП не указана
На похожих ролях по рынку
$178к$212кмедиана$255к
48 в выборке
На СНГ рынке: $4.1к/мес ($3к - $5к)
84
Хорошая вакансия
развернуть
Чёткая ответственность за production-инфраструктуру для AI сочетается с актуальными задачами по агентным системам, но без указанной зарплаты сложно оценить условия оплаты.
Кликните для подробной информации
Зарплата не указанаПередовые технологииЧёткая зона ответственностиЗрелый продуктАктуальная сфера
Оценка от Hirify AI
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
AI & Software Infra Engineer (Agentic AI): Building internal AI platforms, reusable SDKs, MCP servers, and AI-powered infrastructure for reliable engineering systems with an accent on multi-agent workflows, Kubernetes, CI/CD, and production observability. Focus on designing agent planning and recovery mechanisms, integrating LLM capabilities into developer platforms, and implementing security, evaluation, and governance controls.
Location: Remote, Tel Aviv-Yafo, Israel
Company
hirify.global develops behavioral biometrics technology that uses machine learning to analyze digital behavior and help financial institutions prevent fraud and protect online identities.
What you will do
Design and build internal AI platforms, reusable SDKs, libraries, tools, and MCP servers for agentic applications.
Develop single- and multi-agent workflows covering planning, tool selection, delegation, state and memory management, retries, fallbacks, recovery, and human approval.
Integrate AI capabilities into Kubernetes infrastructure and Jenkins or GitHub Actions pipelines to improve development, testing, deployment, and operations.
Implement agent tracing, prompt and tool-call logging, latency and error monitoring, token and cost tracking, regression testing, and failure analysis.
Apply guardrails, access controls, auditability, and governance practices to ensure safe and reliable agent execution.
Own AI platform capabilities from architecture through production and collaborate with engineering and business teams on scalable AI solutions.
Requirements
At least 2 years of hands-on production experience building LLM-powered applications, AI agents, multi-agent systems, or internal AI platforms.
Experience with LangChain, LangGraph, Claude Agent SDK, OpenAI or Anthropic APIs, prompt and context engineering, tool calling, and structured outputs.
Experience building MCP servers and clients, AI evaluations and regression tests, and production observability for traces, prompts, tool calls, latency, errors, tokens, and costs.
At least 5 years of hands-on development experience with Python and/or TypeScript, including asynchronous backend services and APIs with FastAPI or an equivalent framework.
Strong experience with Kubernetes, Helm, Docker, Jenkins, GitHub Actions, and AWS and/or Azure.
Knowledge of Infrastructure as Code, GitOps, Git-based collaboration, AI security controls, auditability, governance, and safe agent execution.
Culture & Benefits
Remote work arrangement for the Israel-based role.
Opportunity to build reusable AI infrastructure adopted across engineering teams.
Hands-on work at the intersection of infrastructure engineering, applied AI, and developer productivity.
Exposure to emerging AI frameworks, models, and cloud technologies.
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 →