Kubernetes & Cloud Infrastructure Engineer – AI Platform

Unleash the power of cloud-native infrastructure — revolutionize AI platforms with your expertise!

Wroclaw-based opportunity with on-site work model

As a Kubernetes & Cloud Infrastructure Engineer – AI Platform, you will be working for our client, a leader in AI innovation, building and managing critical infrastructure that supports advanced AI models and large language model workloads. Your work will directly impact the delivery, scalability, and security of cutting-edge AI solutions, empowering teams across the firm to harness AI's full potential. Join us and be part of shaping the future of intelligent technologies!

Your main responsibilities:

• Build and operate scalable Kubernetes clusters supporting multi-tenancy, GPU workloads, and model serving.
• Manage AWS infrastructure, including networking, IAM, security, and cost optimization.
• Develop and maintain infrastructure as code utilizing tools like Terraform, Helm, and Kustomize.
• Implement and maintain CI/CD and GitOps workflows to streamline deployment pipelines.
• Build observability solutions for system health, utilization, latency, and platform performance monitoring.
• Automate scaling, capacity management, and enforce security and governance policies across cloud and on-premise environments.
• Define and monitor infrastructure Service Level Objectives (SLOs) to ensure reliability and performance.
• Collaborate closely with AI Platform Engineers, Data Scientists, and Research teams to support model inference and deployment infrastructure.
• Enable internal teams through platform tooling, onboarding, and self-service portals.

You're ideal for this role if you have:

• 4+ years of experience in Cloud, DevOps, or Platform Engineering.
• Strong expertise in Kubernetes, including cluster operations, multi-tenancy, GPU scheduling, and Helm/Kustomize.
• Hands-on experience with AWS cloud services—networking, IAM, EKS, EC2, and cost management.
• Proficient in Python and infrastructure-as-code tools such as Terraform.
• Proven ability to build and operate CI/CD and GitOps workflows.
• Skilled in defining and managing infrastructure SLOs.
• Pragmatic, ownership-driven approach and comfortable working in ambiguous environments.

It is a strong plus if you have:

• Experience supporting LLM inference workloads, model serving platforms, or GPU-backed infrastructure.
• Knowledge of RAG systems, vector databases, or AI-related data platforms.
• Background in high-performance or latency-sensitive environments.
• Relevant certifications such as CKA, CKAD, Solutions Architect, or similar.

Language Required for the role:

• Fluent English

Eligibility to work in this role:

• Only candidates with an existing legal right to work in the European Union will be considered for this role.

#MAKEYourCareerBETTER
Interested? Apply now and include your CV (preferably in English) along with a statement confirming your consent to the processing and storage of your personal data.