Staff Engineer, DevTech: Fast AI Inference on GPUs

RadixArk

Palo Alto (CA)

On-site

USD 180,000 - 240,000

Full time

14 days+

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Benefits offered by this job

Equity
Flexible work arrangements

Job summary

RadixArk is seeking a Member of Technical Staff to accelerate LLM inference and training on modern GPUs. You will profile, tune, and implement kernels and model support, with focus areas in inference performance or kernel enablement.

You’ll work closely with partners to translate complex problems into practical, production-ready solutions. You will collaborate across teams to push SGLang and Miles forward, delivering day-0 model support and scalable performance across NVIDIA and AMD platforms.

Qualifications

  • 4+ years in GPU systems, LLM infra, or perf engineering.
  • Strong profiling and debugging across the stack.
  • Hands-on GPU programming in CUDA, ROCm, or Triton.
  • Python and C++ or CUDA proficiency.
  • Ability to translate ambiguous problems into technical plans.

Responsibilities

  • Accelerate AI workloads by profiling and optimizing GPU performance for production workloads.
  • Specialize in one or two tracks: inference performance or kernels and model/hardware enablement.
  • Develop custom CUDA/ROCm/Triton kernels and day-0 model support.
  • Collaborate with ecosystem partners to turn hard problems into concrete wins.
  • Contribute improvements back into SGLang and Miles and roadmap.

Skills

GPU systems
Performance engineering
Profiling
Python
C++
Debugging
Cross-platform
Adaptability

Tools

CUDA
ROCm
Triton
Python
TensorRT-LLM
Megatron
SGLang
Miles

Job description

RadixArk is seeking a Member of Technical Staff to accelerate LLM inference and training on modern GPUs. You will profile, tune, and implement kernels and model support, with focus areas in inference performance or kernel enablement.

You’ll work closely with partners to translate complex problems into practical, production-ready solutions. You will collaborate across teams to push SGLang and Miles forward, delivering day-0 model support and scalable performance across NVIDIA and AMD platforms.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Senior Staff Engineer, Large-Scale AI Inference
Senior Staff Engineer, Large-Scale AI Inference

RadixArk • Palo Alto (CA)

On-site
USD 200,000 - 400,000
Member of Technical Staff — Developer Technology
Member of Technical Staff — Developer Technology

RadixArk • Iowa

On-site
USD 180,000 - 240,000
Equity
Flexible work arrangements
Member of Technical Staff — Inference-Core Engine
Member of Technical Staff — Inference-Core Engine

RadixArk • Palo Alto (CA)

On-site
USD 200,000 - 400,000
Senior GPU Inference Kernel Engineer - Fast & Efficient AI
Senior GPU Inference Kernel Engineer - Fast & Efficient AI

Vidman AI • United States

Remote
USD 140,000 - 210,000
AMD GPU Performance Engineer
AMD GPU Performance Engineer

MindSource • San Francisco (CA)

On-site
USD 140,000 - 190,000
GPU Kernel Architect for Fast LLM Training & Inference
GPU Kernel Architect for Fast LLM Training & Inference

Datadog, Inc. • Paris (TX)

On-site
USD 170,000 - 210,000
Member of Technical Staff - Inference
Member of Technical Staff - Inference

Sail • San Francisco (CA)

On-site
USD 180,000 - 240,000
GPU Kernel Engineer for Fast AI Training & Inference
GPU Kernel Engineer for Fast AI Training & Inference

River AI • Palo Alto (CA)

On-site
USD 200,000 - 420,000
Equity
Visa sponsorship
Relocation assistance
+1
Staff GPU Performance Engineer – Production Inference
Staff GPU Performance Engineer – Production Inference

Speedrun Talent Network • San Francisco (CA)

On-site
USD 210,000 - 360,000
AI Inference Engineer for GPU-Driven LLMs
AI Inference Engineer for GPU-Driven LLMs

Fdetimes • San Francisco (CA)

On-site
USD 140,000 - 240,000