Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
Зарплата и рынок
ЗП не указанаразвернуть
На похожих ролях по рынку
$74к$110кмедиана$178к
7 в выборке
На СНГ рынке: $4.8к/мес ($3к - $5.7к)
78
Хорошая вакансия
развернуть
Роль предполагает серьёзную ответственность за AI-инфраструктуру в продакшене и предлагает сильный пакет льгот, но заметно склеенный и плохо читаемый абзац затрудняет понимание контекста команды и компании.
Сбой в тексте
?Широкая зона ответственности
Современный стек
Сильный пакет льгот
AI-инфраструктура
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Lead AI Platform Engineer (AI infrastructure): Building and operating a production-grade platform for autonomous AI agents with an accent on model serving, low-latency inference, Kubernetes autoscaling, and MLOps. Focus on designing distributed GPU/TPU systems, implementing observability and security controls, and enabling reliable integration through SDKs and CLI tools.
Location: Hybrid work in A Coruña, Bilbao, Gijón, Granada, Madrid, Reus, Sevilla, or Valencia, Spain
Company
T-Systems, part of Deutsche Telekom Group, delivers technology solutions across automotive, healthcare, and public services with a focus on positive societal impact.
What you will do
Design and own the platform for building, deploying, and running autonomous AI agents, including model serving, tool-calling, and state management.
Build high-throughput, low-latency inference services on GPU/TPU clusters and implement autoscaling with Kubernetes and Knative.
Create CI/CD and MLOps pipelines for model versioning, canary releases, and rollback.
Define SLOs and SLIs, implement monitoring with Prometheus and OpenTelemetry, and lead incident response.
Implement IAM, sandboxed execution, data-residency policies, and other platform security controls.
Deliver SDKs, CLI tools, and documentation while mentoring junior engineers and promoting reliable code standards.
Requirements
7+ years of software engineering experience, including 4+ years building large-scale distributed systems.
Proficiency in Go or Rust and Python, with strong experience in Kubernetes, Docker, and Helm.
Hands-on experience with model serving frameworks such as Triton, vLLM, or TensorFlow Serving and GPU/TPU workloads.
Experience with event streaming using Kafka or Pulsar and infrastructure as code using Terraform or Pulumi.
Solid knowledge of LLM concepts, retrieval-augmented generation, and tool-use APIs.
Strong debugging, observability with Prometheus, Grafana, or OpenTelemetry, and security skills involving IAM or Vault.
Excellent communication skills and a focus on shipping reliable, production-grade code.
Nice to have
Ph.D. or M.S. in computer science or a related field.
Experience with serverless runtimes, vector databases such as FAISS or Milvus, or agent frameworks such as LangChain or AutoGPT.
Open-source contributions in AI/ML infrastructure.
Culture & Benefits
International, dynamic, and collaborative work environment with autonomy and continuous support.
Hybrid work model, flexible working hours, and social initiatives through T-Social.
Training through Coursera, weekly English, Spanish, and German classes, international mentoring sessions, and Experience Days.
Flexible compensation including health insurance, meal vouchers, childcare, and transport, plus telemedicine, life and accident insurance, and a social fund.
26+ working days of vacation per year, specialist medical, legal, and wellness services, and 100% salary coverage during medical leave.
Hiring process
Send a CV in English.
Only CVs from candidates meeting the stated requirements will be processed.
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 →