About the Team

The GPT Infrastructure team builds software that turns advanced inference and optimization research into production products. One focus is enabling strategic infrastructure partners and accelerator vendors to qualify and onboard new compute without a bespoke porting and optimization effort for every hardware platform.

We build the control planes, APIs, secure partner-side execution environments, evaluation systems, artifact pipelines, and operational tooling that make these workflows repeatable and trustworthy. The work sits at the intersection of distributed systems, AI inference, compilers and runtimes, performance engineering, security, and external partnerships.

About the Role

We are seeking an experienced systems generalist who can work comfortably across the stack to help build an automated inference optimization platform. Given a workload, target hardware profile, compiler and runtime context, and a trusted verifier, the system runs durable optimization campaigns that generate, compile, execute, grade, and improve candidate kernels, runtime configurations, and serving-stack changes.

You will design both the OpenAI-hosted control plane and the partner-side software that evaluates candidates on real accelerator hardware. The product must keep long-running workflows reliable, make performance results reproducible, and maintain clear trust boundaries around sensitive model and hardware information.

This is a deeply cross-stack role, combining strong software engineering fundamentals with systems thinking and performance intuition. You will work closely with research, inference engineering, infrastructure, security, product, and strategic partners to turn a powerful research workflow into a scalable product.

Key Responsibilities

• Design, build, and operate durable APIs and control-plane services for multi-hour or multi-day optimization campaigns, including scheduling, retries, budgets, checkpoints, artifact lineage, and observability.
• Build secure partner-side runner and grader software that can compile, execute, verify, and benchmark candidate artifacts on third-party accelerator hardware.
• Integrate hardware profiles, ISA and toolchain context, compilers, runtimes, and inference-serving engines into a repeatable optimization workflow.
• Turn research prototypes into reliable product surfaces with clear contracts, debuggable failure modes, reproducible outputs, and excellent developer ergonomics.
• Develop correctness and performance evaluation systems spanning latency, throughput, memory use, utilization, and cost efficiency.
• Build artifact, provenance, and qualification workflows that make optimized kernels, binaries, configurations, and reports safe to review and deploy.
• Collaborate with Research, Inference Engineering, Infrastructure, Security, Product, and Strategic Partnerships to deliver production-ready solutions.
• Drive technical architecture and execution across ambiguous, cross-functional initiatives that connect OpenAI systems with partner environments.

Basic Qualifications

• 8+ years of professional software engineering experience building large-scale distributed systems, infrastructure platforms, or cloud services, or equivalent depth of experience.
• Strong programming skills in one or more of C++, Python, Go, or Rust.
• Experience designing and operating highly available backend systems, APIs, job orchestration systems, or durable workflows for production workloads.
• 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 engineering decisions.
• Proven ability to lead complex technical initiatives as a senior individual contributor and work effectively across organizational boundaries.

Preferred Skills

• Experience with AI infrastructure, inference-serving systems, or large-scale machine learning systems.
• Experience with compilers, runtimes, kernel optimization, or performance engineering; familiarity with technologies such as LLVM, MLIR, Triton, CUDA, or ROCm is a plus.
• Familiarity with GPUs, accelerators, hardware architecture, ISA concepts, or vendor toolchains.
• Experience with inference-serving frameworks or engines such as vLLM, SGLang, Triton Inference Server, or similar systems.
• Experience building developer platforms, external APIs, remote execution systems, or secure partner-facing infrastructure.
• Experience working with strategic cloud, hardware, or infrastructure partners.