About the role
About
the Role RadixArk is looking for a Backend/Platform Engineer to build the API layer, control plane, and platform services that power SGLang and Miles in production. You'll design and implement the REST/gRPC APIs, authentication systems, multi-tenancy isolation, and monitoring infrastructure that thousands of developers and companies rely on. This role bridges high-performance inference/training systems with production-grade platform engineering.
Requirements 4+ years experience building production backend systems, APIs, or platform infrastructure Bachelor's or Master's degree in Computer Science, Engineering, or equivalent industry experience Strong proficiency in Python, Go, or Rust with production-quality code standards Experience designing and building REST/gRPC APIs at scale Solid understanding of distributed systems, databases, caching, and message queues Experience with authentication, authorization, rate limiting, and multi-tenancy Familiarity with cloud platforms (AWS, GCP, Azure) and Kubernetes Experience with monitoring and observability tools (Prometheus, Grafana, DataDog) Understanding of ML serving infrastructure or high-throughput systems is a plus
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 About RadixArk RadixArk is an infrastructure-first company built by engineers who've shipped production AI systems , created SGLang (20K+ GitHub stars, the fastest open LLM serving engine), and developed Miles (our large-scale RL framework). We're on a mission to democratize frontier-level AI infrastructure by building world-class open systems for inference and training. Our team has optimized kernels serving billions of tokens daily, designed distributed training systems coordinating 10,000+ GPUs, and contributed to infrastructure that powers leading AI companies and research labs. We're backed by well-known investors in the infrastructure field and partner with Google, AWS, and frontier AI labs. Join us in building infrastructure that gives real leverage back to the AI community.
