Software Engineer, GPT Infrastructure

The role

You will build a platform to qualify and optimize inference workloads across heterogeneous compute environments. This involves developing OpenAI-hosted services and secure partner-side software for long-lived optimization workflows.

What you will do

• Design, build, and operate APIs and control-plane services for workload qualification and optimization.
• Build secure partner-side execution and evaluation software.
• Integrate model workloads, hardware profiles, compiler toolchains, and distributed-execution backends.
• Develop correctness and performance evaluation systems.
• Automate the generation, evaluation, and improvement of kernels and runtime configurations.
• Diagnose performance and correctness issues across software and hardware boundaries.
• Build artifact-management, provenance, and regression-testing workflows.
• Turn experimental research workflows into reliable product surfaces.
• Collaborate with Research, Inference Engineering, Runtime and Compiler teams, Infrastructure, Security, Product, and Strategic Partnerships.
• Drive technical architecture and execution across ambiguous initiatives.

Required qualifications

• Strong software engineering experience building distributed systems, infrastructure platforms, production services, developer platforms, or orchestration systems.
• Proficiency in one or more systems-oriented languages such as 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.
• Ability to reason about model execution and diagnose problems across software and hardware boundaries.
• Experience using profiling, tracing, benchmarking, and measurement to guide engineering decisions.
• Strong ownership and the ability to work effectively across research, engineering, security, product, and external-partner teams.

Nice to have

• Experience with AI infrastructure, model inference, distributed ML systems, or inference-serving platforms.
• Familiarity with GPU or accelerator architecture, memory hierarchies, interconnects, collective communication, and distributed model execution.
• Experience with compilers, runtimes, kernels, or performance engineering using technologies such as CUDA, ROCm, Triton, LLVM, or MLIR.
• Familiarity with inference engines or serving systems such as vLLM, SGLang, Triton Inference Server, or comparable internal systems.
• Experience with model partitioning, sharding, tensor or expert parallelism, and compute–communication tradeoffs.
• Experience building remote-execution systems, secure partner-facing infrastructure, evaluation harnesses, or artifact pipelines.
• Experience with automated optimization, search systems, coding agents, or evaluator-driven systems.

About the company

OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity.