Senior Cloud Platform Engineer

We are seeking an experienced Senior Cloud Platform Engineer to own the cloud infrastructure and delivery pipeline supporting one of our largest OEM programs. This role is based on-site at the customer's engineering facility, embedded alongside their teams. You will build and operate our GCP-based platform using GitOps and infrastructure-as-code, automate the paths that get software from commit to production, and act as the local owner for cloud access, environment provisioning, and day-to-day operational issues. This is a hands-on role for a broad, self-directed engineer who is comfortable being the on-site technical point of contact and working across organizational boundaries to unblock delivery.

• →Own and evolve our GCP cloud platform for the program - GKE, IAM, Vertex, networking, and supporting services - with a focus on reliability, security, and cost.
• →Build and maintain infrastructure as code in Terraform, treating all environment configuration as reviewed, versioned, and reproducible.
• →Operate the platform using GitOps practices (Argo CD, Helm), so that environment state is declarative and every change is traceable to a commit.
• →Design and maintain CI/CD automation that takes services from commit to deployment with minimal manual intervention, including progressive delivery patterns such as blue/green and canary rollouts.
• →Build observability and alerting that gives both Sonatus and the customer a clear view of system health, and lead troubleshooting when things break.
• →Serve as the on-site owner for cloud access and environment issues - coordinating permissions, provisioning, and workflow questions directly with the customer's IT and platform teams.
• →Manage the program's AI resources - model access, GPU and accelerator capacity, quotas, and API keys across Vertex and other model services - and track usage and spend so teams get the capacity they need within budget.
• →Optimize AI model deployment and serving for latency, throughput, and cost, including model selection, right-sizing, batching, caching, and quantization, and measure the results against agreed benchmarks.
• →Automate recurring operational work and reduce toil, so that developer velocity does not depend on manual intervention.
• →Partner with Sonatus engineering teams in California, Ireland, Korea, and India to keep the on-site environment aligned with our broader platform.

• 7+ years of experience building and operating production cloud infrastructure, with a strong DevOps, platform engineering, or SRE background.
• Deep, hands-on experience with Google Cloud Platform (GKE, IAM, VPC/networking, Cloud Build, or equivalent). Experience with AWS or Azure is welcome, but GCP depth is required.
• Strong Terraform skills and a track record of managing real production infrastructure as code.
• Practical experience with GitOps workflows and tooling (Argo CD, Flux, Helm) and a preference for declarative, version-controlled operations.
• Solid Kubernetes and containerization experience - deploying, scaling, securing, and debugging real workloads.
• Strong automation and scripting ability (Python, Go, or Bash) and a bias toward eliminating manual steps.
• Experience building and maintaining CI/CD pipelines (GitHub Actions, GitLab CI, Jenkins, or similar).
• Comfort operating independently in a customer environment: strong communication, sound judgment on what to escalate, and the credibility to work directly with a partner organization's engineering and IT teams.
• Experience with ML or AI workloads running on cloud infrastructure.

• Experience working embedded at, or delivering into, a large enterprise or automotive customer environment.
• Familiarity with cloud cost management and FinOps practices.
• Security and compliance experience in a regulated or enterprise setting.