Platform Engineer / DevOps

• Workload: full-time
• Contract: B2B, 12 months + extensions
• Business travel: occasionally to Sweden
• 100% remote work
• The team is based in Stockholm, Sweden
• Language: fluent English (Swedish desirable)

We are looking for an experienced DevOps / Platform Engineer to take hands-on ownership of a production AI platform running large language model workloads. This is an individual contributor role with real production responsibility. While the Platform Tech Lead defines the overall technical direction, you will own platform components end-to-end and ensure that the environment remains reliable, secure and predictable in production. The platform runs on Kubernetes with Talos Linux and GPU-enabled nodes, using technologies including NVIDIA NIM and vLLM to serve LLM workloads.

Your responsibilities

• Operating and continuously improving a production-grade Kubernetes platform.
• Taking end-to-end ownership of selected platform components.
• Troubleshooting complex Kubernetes infrastructure and production issues.
• Investigating and resolving issues involving:
• unavailable nodes,
• unhealthy or hanging pods,
• Kubernetes Operators,
• CRDs and controllers,
• unexpected reconciliation behaviour,
• platform and infrastructure dependencies.
• Restoring production services and performing root cause analysis.
• Implementing improvements to prevent recurring incidents.
• Planning and performing safe rolling upgrades of Kubernetes clusters and platform components.
• Supporting highly available and predictable operation of GPU-enabled infrastructure.
• Operating infrastructure supporting LLM inference and model serving.
• Working with technologies such as NVIDIA NIM and vLLM.
• Improving automation, observability and operational processes.
• Creating reusable platform patterns and clear interfaces for product teams.
• Improving developer experience and reducing time-to-market.
• Maintaining strong security and data residency standards.
• Working closely with engineers, infrastructure teams, technical leads and business stakeholders.

We are looking for

• Strong hands-on experience operating Kubernetes in production.
• Deep practical understanding of Kubernetes infrastructure and troubleshooting.
• Experience with cluster lifecycle management and production upgrades.
• Strong Linux administration skills.
• Experience owning production systems and resolving complex incidents.
• Understanding of Kubernetes Operators, controllers and CRDs.
• Strong troubleshooting and root cause analysis capabilities.
• Good understanding of observability, monitoring and production reliability.
• Ability to work independently and take technical ownership.
• Fluent spoken and written English.

Nice to have

• Experience with Talos Linux.
• Experience running Kubernetes on bare metal or self-managed infrastructure.
• Experience with GPU-enabled Kubernetes environments.
• Knowledge of NVIDIA GPU Operator, NVIDIA NIM, CUDA or similar NVIDIA technologies.
• Experience with vLLM or other model-serving / inference technologies.
• Background in AI/ML infrastructure, MLOps or AI platforms.
• Swedish language skills or willingness to develop Swedish over time.