GPT Infra Systems Architect: End-to-End Inference

OpenAI; Seattle (WA); On-site; USD 293,000 - 445,000; Full time

Job summary

OpenAI in Seattle leads the GPT Infrastructure team, delivering an automated inference optimization platform across workloads and hardware profiles. You design OpenAI‑hosted control planes and partner‑side software to evaluate candidates on real accelerator hardware, with reliable long‑running workflows and clear trust boundaries around sensitive model and hardware information.

This deeply cross‑stack role blends software engineering with systems thinking and performance intuition, collaborating

Qualifications

• 8+ years of professional software engineering experience building large‑scale distributed systems or equivalent depth.
• Strong programming skills in C++, Python, Go or Rust.
• Experience designing and operating highly available backend systems, APIs, or durable workflows.
• Strong understanding of distributed systems, Linux, networking, storage, containers, and modern cloud architectures.
• Experience debugging complex systems and using measurement, profiling, and benchmarks to guide decisions.
• Proven ability to lead complex technical initiatives as a senior individual contributor across teams.

Responsibilities

• Design, build, and operate durable APIs and control‑plane services for multi‑hour or multi‑day optimization campaigns.
• Build secure partner‑side runner and grader software to compile, execute, verify, and benchmark artifacts on accelerator hardware.
• Integrate hardware profiles, ISA and toolchain context, compilers, runtimes, and inference engines into a repeatable workflow.
• Turn research prototypes into reliable product surfaces with clear contracts and reproducible outputs.
• Develop correctness and performance evaluation systems spanning latency, throughput, memory use, utilization, and cost efficiency.
• Build artifact, provenance, and qualification workflows for safe review and deployment.
• Collaborate across Research, Inference Engineering, Infrastructure, Security, Product, and Partnerships.
• Drive architecture and execution across cross‑functional initiatives connecting OpenAI systems with partner environments.

Skills

Distributed systems

Backend systems

C++/Python/Go/Rust

Linux

Networking

Containers

Cloud architectures

Debugging complex systems

Lead technical initiatives

Tools

LLVM

MLIR

Triton

CUDA

ROCm

vLLM

Job description

OpenAI in Seattle leads the GPT Infrastructure team, delivering an automated inference optimization platform across workloads and hardware profiles. You design OpenAI‑hosted control planes and partner‑side software to evaluate candidates on real accelerator hardware, with reliable long‑running workflows and clear trust boundaries around sensitive model and hardware information.

This deeply cross‑stack role blends software engineering with systems thinking and performance intuition, collaborating