Destava

Member of Technical Staff — Developer Technology

radixark is hiring for Member of Technical Staff — Developer Technology in Palo Alto. Staff level. First seen November 7, 2026; open as of November 19, 2026. Jobs taken straight from company career pages — no aggregator in between.

Save to applyFree forever. No commitment, no card required.

Company
radixark
Where
Palo Alto
Type
Full-time
Level
Staff
First seen
November 7, 2026
Listed via
Ashby
Open for
11 days, as of November 19, 2026

About this job

RadixArk seeks a Member of Technical Staff, Developer Technology to accelerate and reduce expenses associated with LLM inference and training on contemporary GPUs. This DevTech team role contributes to the SGLang inference engine and the Miles RL training framework, based in Palo Alto.

Responsibilities

  • Assess and enhance GPU performance for actual production workloads across current and upcoming hardware, identifying bottlenecks from individual kernels to distributed multi-node configurations.
  • Concentrate on one or two domains: inference performance, covering engine tuning, benchmarking, long-context and multi-turn optimization, parallelism strategies, and production issue resolution.
  • Concentrate on one or two domains: kernels and model/hardware enablement, involving custom CUDA/ROCm/Triton kernels, low-precision quantization, and immediate support for new models on new silicon.
  • Concentrate on one or two domains: speculative decoding, including draft-model training, acceptance-rate tuning, and cross-platform kernel adaptation.
  • Concentrate on one or two domains: training systems, such as RL post-training with Miles, FP8 training, elasticity, and efficiency for long-rollout and long-context scenarios.
  • Collaborate directly with the ecosystem: convert vague, critical challenges from partner engineers into concrete outcomes, clear technical direction, and reproducible guides.
  • Improve SGLang and Miles: integrate user-driven enhancements into open-source systems and development roadmap.

Requirements

  • At least 4 years in GPU systems, LLM infrastructure, or performance engineering.
  • Robust profiling and debugging capabilities: able to identify root causes of performance and correctness issues throughout the stack.
  • Practical GPU programming expertise in CUDA, ROCm, or Triton, with readiness to operate across multiple platforms.
  • Proficient programming in Python and either C++ or CUDA.
  • Adept at advancing on difficult, ambiguous problems with minimal initial information, and quickly learning unfamiliar systems, codebases, and domains.
  • Capable of converting vague requests into concrete technical strategies, verified guides, and actionable suggestions, while communicating credibly with expert engineering audiences.

Nice to have

  • Thorough understanding of LLM inference internals: distributed serving, parallelism, routing, KV-cache management, and scheduling.
  • Experience with low-precision quantization for inference and training, including FP8, INT8/INT4, with NVFP4 or MXFP4 as a notable advantage.
  • Background in writing and optimizing custom GPU kernels.
  • Working knowledge of speculative decoding techniques like Eagle, DFlash, or DSpark.
  • Familiarity with large-scale distributed training: pre-training, SFT, RL post-training, elasticity, and long-context workloads.
  • Experience optimizing across both NVIDIA and AMD platforms.
  • Direct experience with SGLang, Miles, vLLM, TensorRT-LLM, Megatron, or similar frameworks; involvement in open-source AI/ML projects.

Benefits

  • Stock options

Read more and apply on radixark's site

Questions about this job

When was this Member of Technical Staff — Developer Technology job at radixark posted?

Destava first saw it on November 7, 2026, on radixark's own careers page (Ashby).

Is radixark still accepting applications for it?

It was open on radixark's own site when Destava last read it, on November 19, 2026, 11 days after we first saw it. When the company takes it down, this page says the job has closed.

How do I apply for Member of Technical Staff — Developer Technology at radixark?

On radixark's own site, at jobs.ashbyhq.com: open the posting. Destava does not take the application. Save the job to your Destava board to track it, see how well you fit and tailor your résumé to it.

Is this radixark job posting legit?

Destava read it on radixark's own careers page at jobs.ashbyhq.com, run on Ashby, not on a job board. First seen November 7, 2026. Apply on the company's own site, and never pay to apply for a job.

What other jobs is radixark hiring for?

radixark has 19 open postings on its own site: see all jobs at radixark.

How many business operations specialists, all other jobs are open in San Francisco Bay Area?

230 open, 63 of them new this week, at 151 companies: see them all.

Applying to this one?

See how well you fit, before you apply

Save it to your board. Add your résumé once, and Destava shows where you are strong, what is missing and how to pitch yourself, then tailors your résumé to this posting.

  1. Found it
  2. Save it
  3. See your fit

Free forever. No commitment, no card required.

Or apply on radixark's own site

With Destava: Save to apply · Tailor my résumé · Write a cover letter

This page includes information from the O*NET 31.0 Database by the U.S. Department of Labor, Employment and Training Administration (USDOL/ETA). Used under the CC BY 4.0 license. O*NET® is a trademark of USDOL/ETA.