Tasks:
- * Build Agent developer tools, debugging CLI, visual orchestration, and automated testing
- * Build AI observability for model calls, token usage, inference latency, prompts, and responses
- * Build anomaly alerting for Agent behavior
- * Define AI infrastructure technical roadmaps
- * Design Agent runtime lifecycle and session-state persistence
- * Design multi-tenant AI code execution sandboxes
- * Design single-Agent and multi-Agent orchestration
- * Design trace, metrics, and logging collection and storage
- * Guide engineers in implementing architecture
- * Implement agent tool registration and discovery
- * Implement dynamic resource limits, network policies, and filesystem isolation
- * Optimize sandbox startup and cold start performance
- * Produce architecture designs and lead technical reviews
- * Standardize agent communication protocols and integrate orchestration frameworks
- * Track multi-step Agent reasoning and tool-call success rates
Perks/Benefits:
Skills/Tech stack required:
[Agent Orchestration] [Agent runtime] [Agent Runtime Architecture] [Containerd] [Containerization] [Distributed Systems] [Distributed tracing] [Docker] [Filesystem Isolation] [Firecracker] [Go] [GVisor] [Jaeger] [Java] [JavaScript] [Kata Containers] [Kubernetes] [Kubernetes clusters] [Kubernetes scheduling] [Large-scale] [Large-scale Kubernetes clusters] [Multi-tenancy] [Network Policy] [OpenTelemetry] [Prometheus] [Python] [Resource Isolation] [Runtime architecture] [Sandbox security] [VictoriaMetrics] [WebAssembly runtimes] [Zipkin]
Educational requirements:
[Bachelor's Degree in Computer Science or related field]
Role(s):
[AI Infrastructure Architect] [Architect] [Backend Engineer] [Engineer] [Infrastructure] [Infrastructure Architect] [Infrastructure Engineer]