The vacancy is well-defined but lacks compensation details, affecting overall quality.
no salary info
Job description
Raft Digital Solutions is looking for a Senior DevOps Engineer to design and scale Kubernetes infrastructure and support LLM model inference infrastructure. Join a friendly team focused on AI security challenges.
Responsibilities
### Responsibilities
- Design and scale Kubernetes infrastructure for on-prem and cloud environments (dev/stage/prod)
- Deploy and maintain inference infrastructure for LLM models on GPU
- Support GitLab CI/CD and custom Helm charts
- Consult client DevOps specialists on product deployment and prepare client on-prem builds
- Develop observability and diagnose production incidents
Requirements
### Requirements
- Confident operation of Kubernetes in production: diagnostics, PVC, scheduling, probes, secrets
- Helm / Helmfile — release management, templates, multi-environment
- GitLab CI/CD + Terraform — configured and know it inside out
- Observability stack: Prometheus, Grafana, Loki, OpenTelemetry
- Experience with PostgreSQL, Redis, ClickHouse — migrations, backup/restore, sizing
- English: read technical documentation without a dictionary
### Nice to Have:
- Experience with GPU loads in Kubernetes and vLLM/inference servers
- Experience with Yandex Cloud / Cloud.ru
- Skills in sizing infrastructure (cloud/on-prem)
Conditions
### Conditions
- Startup atmosphere, tackling relevant security challenges in AI
- Full-time (40 hours a week)
- Friendly team ready to support and listen to your ideas
- Professional growth: participation in conferences, training, and development
About Raft Digital Solutions
Raft Digital Solutions is a company focused on developing and integrating AI-based solutions to optimize business processes and improve productivity. Public profiles describe it as an IT/AI solutions provider working with organizations of various sizes.