Drimva

Arm

Staff Software Engineer, AI Inference Cloud

$209K–$283K

Seattle, Washington · Staff · Full-time · Posted Sep 9, 2026

Experience
8+ years of experience, or equivalent proven impact, building distributed systems, cloud platforms, or production infrastructure.
Visa sponsorship
Relocation package, including visa sponsorship support, is available for candidates who require it.

About the job

Shapes technical direction and builds reliable, scalable cloud services and platform capabilities for AI inference workloads.

What you'll do

  • Define architecture and develop Kubernetes platform capabilities for deploying, scheduling, scaling, recovering, and managing AI workloads.
  • Establish production practices and improve platform reliability, performance, observability, and resource efficiency; lead readiness reviews and resolve complex incidents.
  • Lead design and build reviews, mentor engineers, and drive technical alignment across teams.

What they ask for

  • Deep production experience with Kubernetes, including controllers, operators, scheduling, resource management, networking, and workload lifecycle management.
  • Hands-on programming in Go, C++, Rust, Python, or a similar language, with strong software and production engineering skills.
  • Track record of leading complex technical initiatives while remaining hands-on, including architecture, implementation, debugging, mentoring, and influencing technical direction.
  • Ability to troubleshoot complex systems and communicate clearly across technical backgrounds.

Nice to have

  • Experience with AI infrastructure, model serving, or accelerator-backed workloads.
  • Familiarity with PyTorch, Ray, vLLM, SGLang, or TensorRT-LLM, or experience qualifying accelerators and tuning distributed workloads.

Pay

$209,100-$282,900 per year (base salary)

Tools

Kubernetes, Go, C++, Rust, Python, PyTorch, Ray, vLLM

AI focus

Build and operate production cloud infrastructure for AI inference; support AI workloads and improve inference performance and resource efficiency.

Model-written summary · the original posting is authoritative

First seen Oct 28, 2026 · Last verified Nov 5, 2026 (UTC)