Infrastructure Engineer and SRE

Design and operate secure, scalable infrastructure for AI workloads, including untrusted code execution, parallel AI-agent runtimes, multi-cloud and customer VPC deployments, observability, and enterprise integrations.

Responsibilities

• Design systems for large-scale untrusted code execution and sandboxing
• Build massively parallel AI-agent runtime and scheduling systems
• Design multi-cloud and customer VPC deployment architecture
• Develop highly reliable distributed systems with strict security and data guarantees
• Implement observability across AI workflows and infrastructure
• Build enterprise-grade integration and metadata platforms
• Define how AI systems run safely in production

Requirements

• Strong background in distributed systems, scalability, multi-cloud architecture, and security
• Experience with operating systems, containers, Kubernetes, cloud networking, and event-driven runtimes such as Knative or KEDA
• Experience designing, building, and operating large-scale infrastructure
• Passion for building simple, elegant solutions to hard systems problems
• Strong zero-to-one mindset