AI Infrastructure Engineer, Sandbox Platform

Overview

Build and evolve an agent sandboxing platform for secure, high-performance code execution powering agentic workflows in internal and customer-managed environments.

What you'll do

• Design and build the sandboxing platform, client library, and API surface for secure code execution.
• Ensure strong isolation, security, and reproducibility across user sessions and workloads.
• Optimize for cold-start latency, memory footprint, and resource utilization at scale.
• Drive down error rates through debugging, monitoring, and proactive fixes.
• Respond to incidents and production issues with root cause analysis and preventive fixes.
• Develop and maintain a product roadmap for sandboxing from immediate needs to long-term architecture.
• Lead architecture reviews and own projects end-to-end through design and deployment.

What you'll need

• 4+ years of experience building high-performance systems software.
• Experience maintaining libraries, SDKs, or developer-facing APIs.
• Deep understanding of Linux internals including isolation, memory management, cgroups, and namespaces.
• Experience with containerization and virtualization technologies (Docker, Firecracker, gVisor, QEMU, Kata Containers).
• Proficiency in a systems programming language such as Go, Rust, or C/C++.
• Strong debugging skills and ability to navigate performance/security tradeoffs in production systems.