OpenAI
Software Engineer, GPT Infrastructure
$293K–$385K
San Francisco +1 · Hybrid · Full-time · Posted Apr 27, 2026
- Location
- San Francisco
Seattle - Experience
- No specific number of years stated.
About the job
Build and operate infrastructure that qualifies and optimizes model inference workloads across different accelerator platforms, including secure partner-side execution and evaluation software.
What you'll do
- Design and operate APIs and orchestration services for long-running optimization campaigns.
- Build systems to compile, execute, verify, profile, and benchmark candidate artifacts on accelerator hardware.
- Integrate workloads, hardware, compilers, runtimes, and serving systems into repeatable evaluation and optimization workflows.
What they ask for
- Strong software engineering experience building distributed systems, infrastructure platforms, production services, developer platforms, or orchestration systems.
- Proficiency in one or more of Python, C++, Go, or Rust.
- Experience designing and operating APIs, job orchestration systems, durable workflows, or large-scale backend services.
- Strong understanding of Linux, networking, storage, containers, distributed execution, and modern infrastructure architectures.
Nice to have
- Experience with AI infrastructure, model inference, distributed ML systems, or inference-serving platforms.
- Experience with compilers, runtimes, kernels, or performance engineering using technologies such as CUDA, ROCm, Triton, LLVM, or MLIR.
Pay
$293K – $385K USD base salary
Tools
Python, C++, Go, Rust, CUDA, ROCm, Triton, LLVM
AI focus
Automate the generation, evaluation, and iterative improvement of kernels, runtime configurations, parallelization strategies, and serving-stack changes for model inference workloads.
Model-written summary · the original posting is authoritative