Senior DevOps Architect for Scalable AI Sandboxes

Zof AI; San Francisco, Northern (CA, KY); Hybrid; USD 150,000 - 230,000; Full time

Job summary

Zof AI in San Francisco seeks a Senior DevOps Engineer to run the infrastructure that powers fleets of sandboxed agents for safe and cost-effective customer code execution. You will own the execution layer of our control plane: Kubernetes, CI/CD pipelines, isolation, observability, and cost controls.

The role requires production-scale experience, strong security and reliability focus, and the ability to optimize per-agent costs while enabling rapid, safe engineering.

Qualifications

• Experience running production infrastructure on a major cloud platform.
• Working knowledge of Kubernetes, containers, and orchestration.
• Experience building CI/CD pipelines, deployment automation, and infrastructure as code.
• Familiarity with observability, monitoring, and on-call practice.
• Judgment about security, reliability, and cost trade-offs.
• Daily use of AI tools to automate operational and engineering work.
• Clear written and verbal communication.
• Comfort operating in a fast-moving environment.

Responsibilities

• Design and operate the sandboxed environments where agents reproduce defects and validate fixes.
• Own Kubernetes, container, and compute infrastructure end to end.
• Build CI/CD pipelines that let engineers ship safely many times a day.
• Harden isolation boundaries so untrusted customer code stays inside its sandbox.
• Instrument fleet health with metrics, logs, tracing, and alerting that catch failures early.
• Drive down cost per agent run through scheduling, autoscaling, and capacity work.
• Automate provisioning, deployment, rollback, and environment management.
• Partner with engineers to make infrastructure fast and safe to build on.

Skills

Production infrastructure

Cloud platforms

Kubernetes

Containers & orchestration

CI/CD pipelines

Security, reliability, cost trade-offs

Observability & on-call practices

AI tools in operations

Clear communication

Tools

Terraform

Pulumi

gVisor / Firecracker

Job description

Zof AI in San Francisco seeks a Senior DevOps Engineer to run the infrastructure that powers fleets of sandboxed agents for safe and cost-effective customer code execution. You will own the execution layer of our control plane: Kubernetes, CI/CD pipelines, isolation, observability, and cost controls.

The role requires production-scale experience, strong security and reliability focus, and the ability to optimize per-agent costs while enabling rapid, safe engineering.