Member of Technical Staff — Inference

RadixArk is an infrastructure-first company focused on building world-class open systems for AI inference and training. They are seeking a Member of Technical Staff — Inference to design and optimize large-scale AI inference systems, ensuring performance, latency, and throughput across thousands of GPUs.

Responsibilities:

• Design and build large-scale inference systems for frontier AI models
• Optimize latency, throughput, and GPU utilization in production inference
• Develop and improve model serving architectures and runtimes
• Work on batching, scheduling, and memory management strategies
• Collaborate with kernel, compiler, and systems teams on performance optimization
• Debug performance bottlenecks across the stack
• Drive reliability and scalability of inference infrastructure
• Build tooling for observability, profiling, and performance analysis
• Contribute to long-term inference architecture and strategy