Если вы раньше входили через Google, сбросьте пароль для своей Gmail-почты через кнопку «Забыли пароль?» на экране входа. Затем войдите по email и новому паролю.
Если аккаунта ещё нет, зарегистрируйтесь с Gmail-почтой, после подтверждения почты мы предложим задать пароль.
Что нового
Загружаю обновления...
Что нового
Загружаю обновления...
Работа найдется быстрее с подпискойКандидат найдётся быстрее с подпиской
Чтобы адаптировать резюме под вакансию или составить сопроводительное письмо, загрузите резюме
описание
Planet is a technology company transforming payments through integrated payment processing, VAT refunds, dynamic currency conversion, and management services for Retail and Hospitality merchants worldwide.
задачи
Design and build production-grade AI workflows integrating HR, Finance, Operations, and CRM systems;
Implement orchestration logic with triggers, retries, fallbacks, and human-in-the-loop patterns;
Develop and maintain AI agents, prompts, retrieval pipelines, and decision logic;
Own model behaviour in production, including accuracy, usefulness, failure modes, and edge-case handling;
Improve model performance through evaluation frameworks, feedback loops, and real-world usage data;
Define and track success metrics such as accuracy, resolution rate, and time saved;
Diagnose poor outcomes and close the gap between technical operation and business results;
Partner with Data Engineering on shared platforms, infrastructure, CI/CD, data pipelines, security, and governance;
Contribute to shared standards, schemas, and best practices for AI systems.
требования
Strong software engineering background with Python or similar;
Track record of building production systems, not just prototypes;
Hands-on experience with AI/ML systems, including LLMs, classifiers, decision models, or similar;
Experience integrating APIs and working with distributed systems;
Experience designing prompts, retrieval pipelines, or ML inference workflows;
Understanding of model evaluation, monitoring, and feedback loops;
Comfortable working with structured and unstructured data;
Product-oriented approach focused on production outcomes;
Comfortable owning ambiguity and making trade-offs;
English;
Nice to have: workflow orchestration tools such as Temporal, Airflow, or Step Functions; experience building internal tools or agents; familiarity with regulated or enterprise environments; exposure to MLOps or AI evaluation frameworks.
условия
Hybrid work model with three days a week in the office;