On-Device AI OS Engineer: Inference & Performance

OpenAI; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

OpenAI Consumer Devices seeks an Operating Systems Engineer focused on on-device inference to design, develop, and ship the OS stack enabling reliable, responsive, and energy-efficient AI on consumer devices. You will collaborate across OS services, inference runtimes, and research to adapt models to device constraints and production-ready solutions.

The role involves shaping scheduling, memory management, and power strategies, with opportunities to bring capabilities to production through

Qualifications

• Substantial hands-on experience designing, developing, and debugging operating system components or performance-critical software.

Responsibilities

• Build the inference platform: design and implement OS services, frameworks, interfaces for inference execution and lifecycle.

Skills

OS development

C++

ML inference

Scheduling

Performance debugging

Rust

Job description

OpenAI Consumer Devices seeks an Operating Systems Engineer focused on on-device inference to design, develop, and ship the OS stack enabling reliable, responsive, and energy-efficient AI on consumer devices. You will collaborate across OS services, inference runtimes, and research to adapt models to device constraints and production-ready solutions.

The role involves shaping scheduling, memory management, and power strategies, with opportunities to bring capabilities to production through