RadixArk is hiring a Member of Technical Staff — Performance to improve LLM inference and training systems across production workloads. The role focuses on the performance-critical path of SGLang, Miles, and the RadixArk infrastructure stack, including latency, throughput, GPU utilization, memory efficiency, scheduling, batching, kernel behavior, distributed execution, and cost-per-token. The work involves measuring, debugging, and improving systems across NVIDIA, AMD, Google TPU, and cloud partner environments, with attention to metrics such as P99 latency, time to first token, tokens per second per GPU, long-context throughput, cost per million tokens, RL rollout efficiency, and training-inference consistency. RadixArk is an infrastructure-first company building open systems for AI inference and training. The company was founded by AI infrastructure veterans from xAI and NVIDIA and developed SGLang and Miles. The position offers an expected annual salary range of $200,000–$400,000 USD plus equity, depending on background, skills, and experience. RadixArk is an Equal Opportunity Employer.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
Job Type
Full-time
Education Level
No Education Listed