RadixArk is an infrastructure-first company focused on building world-class open systems for AI. They are seeking a Backend/Platform Engineer to design and implement critical API layers and platform services that support their production systems.
Responsibilities:
- Design and build production APIs for SGLang and Miles: REST/gRPC endpoints, client SDKs, API versioning
- Implement authentication, authorization, and rate limiting systems for multi-tenant deployments
- Build control plane infrastructure: job scheduling, resource allocation, model deployment management
- Create monitoring, logging, and observability systems for production inference and training workloads
- Design and implement billing integration, usage tracking, and quota management
- Build management dashboards and admin tools for cluster operations
- Ensure API reliability, performance, and security at scale
- Implement multi-tenancy isolation and security boundaries
- Create deployment automation, CI/CD pipelines, and rollback procedures
- Write comprehensive API documentation and integration guides
- Partner with Systems Engineers to optimize end-to-end latency from API → serving layer
- Debug production issues and implement reliability improvements