обновлено 5 дней назад
DevOps Engineer (AI)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
DevOps Engineer (AI): Deploying and scaling a microservices-based platform on Kubernetes across multiple clouds and on-prem environments with an accent on ML inference optimization and SRE practices. Focus on building robust observability stacks, implementing GitOps/IaC, and managing GPU-based infrastructure for Generative AI.
Location: Remote
Company
develops award-winning AI products focusing on Speech Technologies, NLP, and Generative AI with a privacy-first architecture.
What you will do
- Deploy and evolve a microservices platform in Kubernetes across AWS, GCP, and on-prem (Rancher).
- Operate GPU-based ML inference services (Triton, vLLM) on RunPod, Scaleway, and Nebius.
- Design and maintain CI/CD pipelines using GitHub and GitLab for cloud and on-prem deployments.
- Build and evolve observability systems using Grafana, Prometheus, Loki, and the ELK stack.
- Manage infrastructure as code (IaC) utilizing Terraform and Ansible.
- Ensure platform compliance with SOC 2 requirements and enhance security processes.
Requirements
- Minimum 5 years of experience in DevOps and/or Site Reliability Engineering.
- Strong hands-on experience with Linux system administration and scaling Kubernetes.
- Advanced expertise in Terraform, Ansible, and Python.
- Deep practical experience with at least one major cloud provider, preferably GCP.
- Strict adherence to GitOps and CI/CD principles.
- Ability to operate in high-uncertainty startup environments with evolving requirements.
Nice to have
- Experience with ML inference on GPU/CPU.
Culture & Benefits
- Work with cutting-edge Generative AI, LLMs, and voice-first agentic architecture.
- High engineering bar with real ownership and direct impact on production.
- Fast career progression within a senior-heavy team.
- Fully remote work arrangement.
- 21 vacation days, 5 sick days, and public holidays.
- Private English lessons via Preply.
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 →