DevOps / Platform Engineer (Cloud, Kubernetes, AI Infra)

Role overview Own the cloud and platform foundations behind production services, including systems with AI workloads, vector databases, and real-time inference. The role focuses on reliable operations across cloud environments and Kubernetes, with infrastructure managed as code and deployments designed for monitoring and rollback.

Responsibilities - Design and maintain cloud infrastructure across regions on AWS and GCP. - Operate production Kubernetes clusters, including autoscaling, monitoring, and cost management. - Develop Terraform modules and manage infrastructure changes through code. - Build secure CI/CD pipelines for building, testing, scanning, and deploying services. - Maintain observability and service-level objectives, and participate in an on-call rotation. - Control costs for AI infrastructure, including compute and vector database choices. - Apply security practices such as secrets management, network segmentation, and audit logging. - Provide self-service platform capabilities that help engineering teams deploy independently.

Requirements - At least four years of production experience in DevOps, platform engineering, or SRE. - Strong AWS or GCP knowledge, including networking, identity and access management, load balancing, and multi-region replication. - Production Kubernetes operations experience, with Helm and operators. - Terraform skills covering module design, state, drift detection, and multi-account or multi-region setups. - CI/CD experience with GitHub Actions, GitLab CI, or a comparable system, including pipeline security. - Familiarity with observability tools such as Prometheus, Grafana, Datadog, or ELK. - Linux and Bash skills, plus Python or Go scripting; strong English communication for technical discussions.

Benefits and work setup The role includes an on-call rotation and emphasizes reliable releases with rollback practices.