RadixArk is seeking a Solutions Engineer to help customers successfully deploy and optimize SGLang and Miles for their production workloads. You'll work directly with AI companies, research labs, and enterprises to design architectures, debug performance issues, and ensure they get maximum value from our infrastructure. This role combines deep technical expertise with customer success—you'll be the technical partner customers rely on to ship AI applications at scale.

RadixArk is seeking a Developer Advocate to build and engage our technical community around SGLang, Miles, and our open-source infrastructure. You'll create technical content, give conference talks, host workshops, and work directly with developers to help them succeed with our systems. This role combines deep technical expertise with community building—you'll be the bridge between our engineering team and the thousands of developers using RadixArk's infrastructure.

RadixArk is looking for a Diffusion Inference Engineer to optimize high-performance serving systems for image and video generation models. You'll push the limits of inference efficiency for models like Flux-1, Flux-2, Wan 2.1/2.2, and next-generation architectures, integrating them into SGLang's serving infrastructure. This role focuses on making diffusion inference faster, cheaper, and more scalable in production.

RadixArk is seeking a Brand Marketing Manager to build our presence in the AI infrastructure community and tell the story of SGLang, Miles, and our mission to democratize frontier AI systems. You'll craft compelling narratives, manage our brand across channels, coordinate with engineering teams on technical content, and build relationships with developers, researchers, and industry leaders. This role requires both strategic thinking and hands-on execution in a technical, open-source environment.

RadixArk is seeking a Recruiting Coordinator to support our hiring efforts as we build a world-class engineering team. You'll coordinate interview scheduling, manage candidate communications, and ensure a seamless experience for candidates joining our infrastructure-focused company. This role is perfect for someone who is highly organized, loves logistics, and wants to help build the team that's democratizing AI infrastructure.

RadixArk is seeking an Executive Assistant to support our founding team as we scale world-class AI infrastructure. You'll work directly with our founders to manage complex schedules, coordinate high-stakes meetings with investors and partners, and handle confidential matters with discretion. This role requires exceptional organizational skills, strong judgment, and the ability to thrive in a fast-paced technical environment where priorities shift rapidly.

RadixArk is seeking an Office Manager to create a productive, welcoming environment for our engineering-focused team in San Francisco. You'll manage day-to-day office operations, coordinate team events, support travel and logistics, and ensure our office runs smoothly so engineers can focus on building world-class AI infrastructure. This role is ideal for someone who thrives in fast-paced startup environments and enjoys being the operational backbone of a technical team.

RadixArk is seeking a Lead DX Engineer – Documentation to be the founding member of our developer experience team and own our documentation strategy. Documentation is critical to SGLang's success as the fastest open LLM serving engine and Miles as our RL training framework—this role will directly impact how thousands of developers deploy and optimize AI infrastructure. You'll report to our Head of Engineering and have the opportunity to build your own team as we scale. This role is for a senior engineer who is obsessed with developer experience, enjoys writing and educating developers, and wants to lead building world-class docs for production AI infrastructure. We're looking for someone with expertise to lead comprehensive documentation efforts and drive adoption among the global AI systems community.

RadixArk's Compute & Business Operations team ensures we have the GPU and TPU capacity, vendor coordination, and operational discipline needed to power SGLang, Miles, and our production infrastructure. We work across Engineering, Finance, Product, and Research to keep compute predictable, cost-efficient, and aligned to company priorities. We're looking for a highly organized BizOps generalist who can thrive in a fast-moving, technical environment—someone who can track hardware inventory and contracts, coordinate procurement across cloud providers, manage cross-functional workflows, and surface risks early to keep our infrastructure running smoothly.

RadixArk is launching a full-time, paid, 1-year residency program for aspiring AI infrastructure engineers. You'll rotate across inference, training, kernels, compilers, and cluster infrastructure, working on real production systems alongside senior engineers. This is an opportunity to learn from the team behind SGLang and Miles while owning meaningful projects that impact thousands of developers.

RadixArk is looking for an RL Systems Engineer to build large-scale reinforcement learning systems for post-training, fine-tuning, and alignment. You'll work on Miles, our open-source RL framework, scaling workloads across multi-node clusters and optimizing throughput, stability, and cost for frontier model development. You'll partner closely with model researchers, systems engineers, and infrastructure teams to productionize RL at scale.

RadixArk is looking for a Cluster & Infrastructure Engineer to build and operate large-scale AI clusters that power frontier-level training and inference workloads. You'll design reliable infrastructure for multi-node, multi-rack GPU and TPU systems, optimize cluster utilization and scheduling efficiency, and ensure fault tolerance at scale for SGLang and our production systems.

RadixArk is looking for a Generalist Systems Engineer to work across the entire AI systems stack—from kernels to Kubernetes—building and optimizing large-scale inference and training infrastructure. You'll tackle whatever hard problems need solving to push SGLang and our systems forward, rapidly ramping up on new hardware platforms and debugging critical performance issues across the full stack.

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.

RadixArk is looking for a TPU Systems Engineer to build high-performance inference and training systems using JAX, XLA, and Pallas. You'll push large-model workloads to their limits on TPU hardware, working on SGLang-JAX and other critical infrastructure that enables efficient deployment of frontier models on Google's tensor processing units.

RadixArk is looking for a GPU Kernel Engineer to develop high-performance kernels that power SGLang and our next-generation LLM serving infrastructure. Relevant experience includes implementing CUDA, Triton, or Pallas kernels for transformer architectures, with a focus on attention mechanisms, memory optimization, and inference/training runtime integration.