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
$90к$106кмедиана$146к
25 в выборке
На СНГ рынке: $4.6к/мес ($3.6к - $5.4к)
86
Хорошая вакансия
развернуть
Роль чётко сосредоточена на платформенной инженерии для LLM и даёт практический опыт с GPU-инфраструктурой и современными инструментами инференса, хотя работа над клиентскими проектами может означать частую смену контекста.
?Клиентская работа
Передовой стек
Сфера ИИ
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Senior AI/LLM Platform Engineer (GPU Infrastructure/Cloud): Building and operating on-premise and cloud platforms for deploying, serving, and scaling open-weight LLMs with an accent on GPU infrastructure, inference optimization, and secure platform administration. Focus on benchmarking throughput and latency, managing multi-GPU deployments, evaluating inference engines and hardware, and supporting engineering teams and AI agents.
Location: Sofia, Bulgaria; hybrid. The listing also mentions Egypt.
Company
An international engineering firm helping businesses operate with AI at the core, combining engineering expertise with AI-native thinking across industries, technologies, and markets.
What you will do
Design and build on-premise and cloud environments for hosting LLMs.
Deploy, serve, and scale open-weight models behind standard OpenAI-compatible APIs.
Optimize models and serving configurations for throughput, latency, and GPU cost; benchmark results.
Administer platform upgrades, capacity planning, access control, quotas, and the model catalog.
Monitor performance, GPU utilization, usage, and cost; evaluate new models, inference engines, and hardware.
Secure the environment, isolate client data, control access, and support engineering teams and AI agents.
Requirements
5+ years of experience in platform engineering, DevOps, infrastructure, or ML infrastructure.
Hands-on experience deploying and serving open-weight models such as Llama, Qwen, Mistral, or Gemma with vLLM, SGLang, Ollama, or llama.cpp.
Practical knowledge of inference optimization, including quantization, batching, multi-GPU deployment, and matching models to available hardware.
Experience with GPU infrastructure, including NVIDIA drivers, CUDA, GPU scheduling on Kubernetes, and GPU utilization monitoring.
Experience with on-premise infrastructure and at least one cloud provider—AWS, GCP, or Azure—including GPU and AI services.
Strong Docker, Kubernetes, and infrastructure-as-code skills with Terraform or OpenTofu.
Hands-on experience with at least one modern AI coding tool, such as Claude Code, Codex, Cursor, or GitHub Copilot.
Fluent English required.
Nice to have
Experience with LLM gateways and routing, such as LiteLLM, and LLM observability.
Culture & Benefits
Hybrid work in Sofia.
Work on AI-native engineering and business use cases across client projects.
Opportunity to explore new models, inference engines, and hardware as the field evolves.
Respectful and inclusive environment with equal opportunities regardless of personal characteristics.
Hiring process
Submit a CV describing core skills and career goals.
Complete a talent call, technical interview, and, for some roles, a customer interview.
Successful candidates receive an offer and join the company.
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 →