Destava

Member of Technical Staff — Inference-TPU

radixark is hiring for Member of Technical Staff — Inference-TPU 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
12 days, as of November 19, 2026

About this job

RadixArk is hiring a TPU systems engineer to develop high-performance inference and training systems with JAX, XLA, and Pallas. The position centers on enhancing large-model workloads on Google TPUs and advancing open-source infrastructure such as SGLang-JAX. This role is located in Palo Alto.

Responsibilities

  • Develop high-performance inference and training systems with JAX, XLA, and Pallas, including SGLang-JAX
  • Maximize large-model workload performance on the latest TPU hardware
  • Enhance end-to-end latency and throughput for LLM serving on TPU infrastructure
  • Create and implement SPMD strategies for effective distributed inference and training
  • Create and implement Pallas kernels for operations needing specialized low-level control for optimal performance
  • Analyze and refine XLA compilation pipelines and HLO graph transformations
  • Work with kernel engineers and compiler teams to secure performance gains across the stack
  • Contribute to open-source projects with TPU optimization guides, benchmarks, and architectural insights

Requirements

  • 3+ years of experience in building production ML systems with JAX/Torch, XLA, or TPU-focused frameworks
  • Bachelor's or Master's degree in Computer Science, Electrical Engineering, or equivalent industry experience
  • Strong performance tuning skills across compiler and runtime layers
  • Experience with distributed inference systems (e.g., SGLang, vLLM) or training frameworks (e.g., Miles, Alpa, Pathways)
  • Proficiency in Python with a proven record of writing high-performance, production-quality code
  • Experience in developing custom GPU/TPU/AI Accelerator kernels

Nice to have

  • In-depth knowledge of XLA internals: HLO, MLIR, operator fusion, SPMD partitioning, and sharding strategies
  • Familiarity with Pallas for kernel development

Benefits

  • Equity

Read more and apply on radixark's site

Questions about this job

When was this Member of Technical Staff — Inference-TPU 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, 12 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 — Inference-TPU 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 physical therapist aides jobs are open?

910 open, 287 of them new this week, at 131 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.