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

Role overview

Build and operate cloud platforms for production services, including systems with demanding AI workloads such as vector databases, LLM orchestration, and real-time inference. The role covers multi-region AWS and GCP environments, production Kubernetes, infrastructure as code, delivery pipelines, security, and operational reliability.

Responsibilities

- Design and maintain cloud infrastructure across multiple regions on AWS and GCP. - Operate EKS or GKE clusters, including autoscaling, monitoring, and cost management. - Create and maintain Terraform modules and manage infrastructure state and drift. - Build secure CI/CD pipelines for testing, scanning, and multi-region deployments. - Run observability systems, define SLOs, and participate in an on-call rotation. - Control infrastructure costs, including compute and GPU use and vector database capacity. - Implement security practices for secrets, network boundaries, and audit logs, and provide self-service deployment tools to engineering teams.

Requirements

- Four or more years in DevOps, platform engineering, or SRE roles in production environments. - Strong AWS or GCP knowledge, including VPCs, IAM, networking, load balancing, and multi-region replication. - Production Kubernetes operations experience, including Helm and operators. - Terraform skills covering module design, state management, 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 administration and scripting with Bash and Python or Go. - Strong English communication for client architecture discussions.