4 months ago
Berlin, GermanySenior
Responsibilities
- Own the reliable day-to-day operation of platform infrastructure services within the AI Business Unit.
- Drive automation across operational workflows to improve efficiency, scalability, maintainability, and security.
- Support the migration of internal applications from Nomad to Kubernetes and collaborate with Infrastructure teams to improve Kubernetes environments.
- Manage and support Qdrant, PostgreSQL, ClickHouse, Redis, Dify, Langfuse, Kubeblocks, and the Cnpg.io Postgres Operator.
- Build and improve monitoring, alerting, and operational observability standards.
- Enable development teams to design, ship, and operate production-grade Kubernetes-ready services.
- Improve system reliability, scalability, security, and operational excellence across the AI landscape.
Requirements
- Strong hands-on experience with Kubernetes in production environments.
- Experience operating databases and cloud-native services.
- Familiarity with monitoring and observability tools.
- A strong automation mindset and commitment to zero-downtime operations.
- Curiosity and motivation to understand the operational behavior of modern AI technologies.
- Strong focus on reliability, quality, security, ownership, and continuous improvement.
- Fluent English communication skills.
Benefits
- Flat hierarchies, decision-making freedom, and ownership of responsibilities.
- Professional development and training tailored to individual needs.
- Flexible working hours and a trust-based work schedule.
- Hybrid work model with three days of remote work.
- Regular constructive feedback sessions and support for targeted development.
- Support from INSITE during difficult professional or personal life situations.
- Inclusive corporate culture and equal opportunities.
- Additional benefits including a mobility allowance, sports programs, and events.
Tech Stack
Categories
