Назад
Company hidden
6 дней назад

AI Platform Engineer (AI)

Формат работы
hybrid
Тип работы
fulltime
Английский
b2
Страна
CR
Вакансия из списка Hirify.GlobalВакансия из Hirify Global, списка международных tech-компаний
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/
TL;DR
AI Platform Engineer (AI): Building and operating secure, self-hosted AI inference infrastructure for internal large language model usage with an accent on multi-GPU systems, model serving, observability, and developer enablement. Focus on benchmarking open-weight models, optimizing throughput and latency, automating infrastructure, and designing quotas, routing, and queue prioritization.

Location: Prague, Czech Republic; hybrid

Company

hirify.global is a security-first crypto company behind Trezor, the inventor of the first hardware wallet.

What you will do

  • Own the lifecycle of a dedicated multi-GPU inference server, including the operating system, storage, networking, observability, and alerting, in collaboration with IT.
  • Build, deploy, upgrade, and tune the internal model-serving stack using technologies such as vLLM, SGLang, LiteLLM, and Open WebUI.
  • Benchmark and evaluate open-weight model releases for quality, throughput, and latency, and recommend suitable models.
  • Manage quotas, routing, cost and usage reporting, queueing, and prioritization across teams, including cloud model usage when needed.
  • Support developers integrating internal models into IDE assistants, agents, CI pipelines, and internal applications.
  • Maintain APIs, endpoints, documentation, onboarding guides, workshops, and office hours.

Requirements

  • Hands-on coding experience and infrastructure-as-code skills with Ansible, Terraform, Docker, or Kubernetes.
  • Linux systems administration experience covering networking, storage, containers, systemd, and kernel-level troubleshooting.
  • Genuine interest in the open-weight model ecosystem and a service-oriented approach to supporting engineers.
  • English required for daily work.

Nice to have

  • Production or serious homelab experience serving LLMs with vLLM, SGLang, llama.cpp, Ollama, or similar tools.
  • NVIDIA GPU operations experience with drivers, CUDA, NVLink, MIG, nvidia-smi, or DCGM.
  • Datacenter experience involving rack power budgets, liquid cooling, or hardware vendor support.
  • Experience with fine-tuning, LoRA, quantization, or model evaluation methodology.
  • Czech language skills.

Culture & Benefits

  • High ownership and freedom in a pioneering, security-first, open-source environment.
  • Flexible working hours and a supportive, transparent culture.
  • Option to get paid in bitcoin.
  • Professional development budget for training, courses, and workshops.
  • Renovated office with a gym, recreational facilities, 3D printer, free parking, and additional wellness benefits.

Hiring process

  • Submit a CV and a few words about yourself for application review.

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 →