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
The role requires an EU work permit.
Deloitte provides professional services in audit, consulting, advisory, and tax. The organization supports businesses by delivering strategic solutions and leveraging advanced technologies to address complex operational challenges.
задачи
Design, develop, and deploy complex, multi-step AI agents using LangChain, LangGraph, and ADK;
Implement mechanisms for agents to utilize external APIs, custom Python functions, and specialized tools;
Leverage Vertex AI services to manage the agent lifecycle from testing to production deployment;
Integrate and manage foundational models and utilize Vertex AI Training for model customization;
Utilize GCP infrastructure including Compute, GKE, and Cloud Run for deployment;
Adhere to networking standards such as VPC, Load Balancing, and Cloud DNS;
Implement testing and logging to monitor agent behavior, optimize token usage, and ensure reasoning accuracy;
Document agent architectures and promote reusable design patterns.
требования
Exceptional expertise in Python for ML development and API integration;
Experience in building and orchestrating AI workflows using LangChain, LangGraph, and ADK;
Practical experience with Generative AI tasks including function calling, code generation, classification, and prompt engineering;
Understanding of RAG techniques for grounding models;
Strong working knowledge of GCP GenAI and MLOps tools including Vertex AI Agent Builder, Workbench, Pipelines, and Training;
English proficiency;
EU work permit;
Nice to have: Graph databases (e.g., Neo4j), low-latency deployment optimization, data security and PII/PHI handling, advanced MLOps with GKE or Cloud Run.