Senior Systems Engineer, AI Inference Platform

Slope; San Francisco (CA); On-site; USD 180,000 - 260,000; Full time

Job summary

OpenAI in San Francisco is seeking an experienced systems generalist to build an automated inference optimization platform across hardware, compiler, and runtime contexts. You will design the OpenAI-hosted control plane and partner-side software, focusing on reliable long-running workflows, reproducible performance results, and secure handling of model and hardware data.

This cross-stack role collaborates with research, infrastructure, security, product, and partnerships to deliver scalable,

Qualifications

• 8+ years of professional software engineering in large-scale distributed systems.
• Strong programming in C++, Python, Go, or Rust.
• Experience designing and operating backend systems and durable workflows for production workloads.
• Strong understanding of distributed systems, Linux, networking, storage, containers, and cloud architectures.
• Ability to lead complex technical initiatives as a senior individual contributor.

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 for compiling, executing, and benchmarking artifacts on accelerator hardware.
• Integrate hardware profiles, toolchains, compilers, runtimes into repeatable optimization workflows.
• Turn research prototypes into reliable product surfaces with contracts, debuggable failure modes, reproducible outputs.
• Develop evaluation systems spanning latency, throughput, memory usage, utilization, and cost efficiency.
• Build provenance and qualification workflows for safe review and deployment of optimized artifacts.
• Collaborate with Research, Inference Engineering, Infrastructure, Security, Product, and Partnerships.
• Drive architecture across cross-functional initiatives linking OpenAI systems with partner environments.

Skills

C++

Python

Go

Rust

Linux

Networking

Cloud

Tools

LLVM

MLIR

Triton

CUDA

ROCm

Job description

OpenAI in San Francisco is seeking an experienced systems generalist to build an automated inference optimization platform across hardware, compiler, and runtime contexts. You will design the OpenAI-hosted control plane and partner-side software, focusing on reliable long-running workflows, reproducible performance results, and secure handling of model and hardware data.

This cross-stack role collaborates with research, infrastructure, security, product, and partnerships to deliver scalable,