RadixArk
Member of Technical Staff — Inference-Core Engine
$200K–$400K
Palo Alto +1 · On-site · Staff · Full-time · Posted Feb 17, 2026
- Location
- Palo Alto
San Francisco - Experience
- 5+ years in systems engineering, ML infrastructure, or performance-critical backend systems.
About the job
Build and optimize large-scale inference systems that serve frontier AI models, improving performance, reliability, and scalability.
What you'll do
- Design inference systems, serving architectures, and runtimes for frontier models.
- Optimize latency, throughput, GPU utilization, batching, scheduling, and memory management in production.
- Debug performance bottlenecks and build tools for observability, profiling, and performance analysis.
What they ask for
- Strong expertise in large-scale inference systems for LLMs or generative models.
- Deep understanding of GPU architecture and performance characteristics.
- Experience optimizing latency- and throughput-critical production systems, profiling compute-intensive workloads, and debugging across system layers.
- Strong knowledge of distributed systems and networking fundamentals; proficiency in Python, Rust, C++, or Go for production systems.
Nice to have
- Experience with LLM serving stacks such as SGLang, vLLM, or TensorRT-LLM; familiarity with CUDA, Triton, or custom kernel optimization.
- Open-source contributions in ML or systems infrastructure; experience running inference at scale (1000+ GPUs) or a background in HPC/high-performance systems.
Pay
$200,000 - $400,000 USD annual salary (base salary)
Tools
Python, Rust, C++, Go, SGLang, vLLM, TensorRT-LLM, CUDA
AI focus
Develop and optimize infrastructure for large-scale inference of frontier AI models.
Model-written summary · the original posting is authoritative