RadixArk
Member of Technical Staff — Performance
$200K–$400K
Palo Alto +1 · On-site · Staff · Full-time · Posted May 17, 2026
- Location
- Palo Alto
San Francisco
About the job
Improve and measure the performance of LLM inference and training systems across production workloads and hardware environments.
What you'll do
- Analyze and optimize performance across SGLang, Miles, and RadixArk production deployments.
- Benchmark workloads and investigate performance issues across GPUs, TPUs, and cloud environments.
- Build profiling and benchmarking tools, develop performance tuning strategies, and contribute insights to open-source projects.
What they ask for
- Strong systems engineering background, especially in performance-critical software.
- Experience with GPU systems, distributed systems, inference serving, ML runtimes, or high-performance computing.
- Familiarity with profiling, performance debugging, tracing, and benchmark methodology.
- Comfort working with Python and C++.
Nice to have
- Experience with CUDA, Triton, Pallas, ROCm, XLA, or kernel-level optimization.
- Production AI infrastructure, cloud GPU environments, or open-source ML systems experience.
Pay
$200,000 - $400,000 USD annual salary + equity (equity amount not stated)
Tools
SGLang, Miles, Python, C++, CUDA, Triton, Pallas, ROCm
AI focus
Optimize LLM inference and training performance, including latency, throughput, memory use, scheduling, and cost-per-token.
Model-written summary · the original posting is authoritative