SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
RadixArk is seeking a Backend/API Platform Engineer to design and build the production API layer, control plane, and platform services powering SGLang and Miles—AI/ML serving infrastructure used by thousands of developers and companies.
You will own the full stack of platform engineering: designing and implementing REST/gRPC APIs, building authentication and authorization systems, implementing multi-tenancy isolation, and creating monitoring and observability infrastructure. Key responsibilities include building control plane infrastructure for job scheduling, resource allocation, and model deployment management; designing billing integration, usage tracking, and quota management systems; creating management dashboards and admin tools for cluster operations; and ensuring API reliability, performance, and security at scale.
You'll also implement deployment automation and CI/CD pipelines, write comprehensive API documentation, and partner with systems engineers to optimize end-to-end latency from the API layer through the serving layer. This role bridges high-performance inference and training systems with production-grade platform engineering.
Required: 4+ years building production backend systems, APIs, or platform infrastructure. Strong proficiency in Python, Go, or Rust. 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 tools (Prometheus, Grafana, DataDog). Bachelor's or Master's in Computer Science, Engineering, or equivalent. Understanding of ML serving infrastructure or high-throughput systems is a plus.
