Cloud Platform Engineer

What you'll do

• Operate and evolve a Kubernetes-based platform for AI workloads including LLM gateways and agent runtimes.
• Manage access to cloud-hosted foundation models including routing, quotas, cost controls, and tenant isolation.
• Deliver infrastructure as code and GitOps workflows using tools like Terraform and Argo CD.
• Build monitoring, alerting, and tracing systems for AI workloads using OpenTelemetry, Prometheus, and Grafana.
• Design and prototype self-hosted model serving for GPU workloads and inference runtimes.
• Harden the platform with secrets management, network policies, authentication, authorization, and audit logging.
• Support internal product teams through technical documentation, onboarding, and troubleshooting.

What we're looking for

• 3+ years of experience in platform, DevOps, SRE, or cloud engineering.
• Hands-on experience with Kubernetes, including deployments, networking, and troubleshooting.
• Experience with infrastructure as code using Terraform and GitOps tooling like Argo CD or Flux.
• Solid experience with at least one major cloud provider, specifically Azure or AWS.
• Scripting and coding skills in Python, Go, or Bash, along with CI/CD experience.
• Experience with observability tools such as OpenTelemetry, Prometheus, and Grafana.
• Experience with LLM gateways, proxies, or LLM observability and tracing tools (preferred).
• Experience running GPU workloads or model inference serving (preferred).