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
AddanEx International provides staffing and IT consulting services. The client is setting up a central AI governance platform serving developers across a decentralised group, with a focus on cheaper, faster, and more reliable access to AI vendors.
задачи
Build and operate the AI gateway with SSO, per-request logging, data-classification tagging, policy enforcement, and model routing on Azure using Azure OpenAI / AI Foundry, Entra ID, and APIM;
Stand up a governed agent repository with approved agents, owners, permissions, and data scopes;
Build a cost telemetry pipeline attributing every request to a cost centre and use case;
Automate access provisioning and seat lifecycle for each current and future AI tool licence;
Produce developer golden paths, including RAG, agent, and evaluation templates;
Establish observability and runbooks so L1 support can operate routine platform work;
Build and operate production Kubernetes workloads used by other teams;
Develop API gateway or LLM proxy capabilities;
Build practical LLM applications involving API integration, token cost behaviour, evaluation, and RAG patterns;
Own production observability;
Build internal platforms or developer services adopted voluntarily by other teams.
требования
Previously built an AI governance platform end to end, including components such as a gateway, agent repository or registry, policy enforcement, usage and cost telemetry, and access provisioning;
Able to walk through a previously built platform, what it governed, who used it, and what would be done differently;
Experience running containerised workloads that other teams depended on in production Kubernetes;
Experience with API gateway or LLM proxy engineering, such as APIM, Kong, LiteLLM, or equivalent;
Practical LLM application experience with API integration, token cost behaviour, evaluation, and RAG patterns;
Production observability ownership using OpenTelemetry, Grafana, Log Analytics, or equivalent;
Strong backend engineering skills in Python and/or TypeScript;
Experience with IaC and CI/CD using Terraform, GitHub Actions, or Azure Pipelines;
Experience with identity and access engineering, including SSO, RBAC, and service principals;
Experience building an internal platform or developer service that other teams adopted voluntarily;
ML/data-science depth is not required because this is a platform role, not a modelling role;