← All roles

Member of Technical Staff — Developer Technology

RadixArk· Member of Technical Staff
Apply on company site
Palo Alto, CA$200k - $400kFull-timePosted 3mo ago

About the role

Role focused on accelerating LLM inference and training on modern GPU hardware, profiling and optimizing GPU performance, enabling new models and hardware, building kernels, and supporting production workloads for SGLang and Miles.

Responsibilities

  • Accelerate AI workloads. Profile and optimize GPU performance for real production workloads on current and next-generation hardware, root-causing bottlenecks from kernels to distributed multi-node systems.
  • Go deep in one or two focus areas. The team collectively covers the full stack; each engineer specializes in one or two tracks: Inference performance; Kernels and model/hardware enablement; Speculative decoding; Training systems.
  • Partner directly with the ecosystem. Turn ambiguous, high-stakes problems from expert engineers at key partners into concrete wins, clear technical guidance, and reproducible cookbooks.
  • Enhance SGLang and Miles. Feed user-driven improvements back into open-source systems and roadmap, so every win compounds across the ecosystem.

Qualifications

  • 4+ years of experience in GPU systems, LLM infrastructure, or performance engineering.
  • Strong profiling and debugging skills: able to root-cause performance and correctness issues across the stack.
  • Hands-on GPU programming experience in at least one of CUDA, ROCm, or Triton, and willingness to work across platforms.
  • Strong programming skills in Python plus C++ or CUDA.
  • Comfortable making progress on hard, ambiguous problems with little context to start from, and fast to ramp into unfamiliar systems, codebases, and domains.
  • Ability to translate ambiguous asks into clear technical plans, verified cookbooks, and actionable recommendations, and to communicate credibly with expert engineering audiences.

Skills

Required:GPU performance profiling and debuggingGPU programming (CUDA/ROCm/Triton)PythonC++ or CUDASystems thinking and ambiguity managementTechnical communication to expert audiences
Nice to have:Distributed systems / multi-node perfSGLang / Miles / Megatron / TensorRT-LLM
Last updated Aug 18, 2026. Interested? Apply on the company site.
RadixArk logo

About RadixArk

SHIP AI FOR ALL

RadixArk is an infrastructure-first, deep-tech company building large-scale inference and training systems for the entire AI community.

AI systemsMilesSGLangbessemer-ai-infrastructure-2026inferenceinference-inflection-pointinfrastructureopen infrastructure
Company profileWebsite

More open roles at RadixArk