Operating Systems Engineer, On-Device Inference | Consumer Devices

OpenAI
San Francisco
Workplace: OnsiteFull timeUSD 230,000 - 385,000 annuallyFunction: IT Operations (Systems/Network Admin)Skills: ["Debugging","Cross-disciplinary collaboration","Technical decision-making","Performance optimization","Measurement-driven improvement"]

Design and ship the operating system stack that enables reliable, responsive, and energy-efficient on-device AI inference. Build OS services and inference platform interfaces, integrate and optimize inference runtimes, adapt models to device constraints via quantization and memory optimization, and develop scheduling/resource policies for latency, memory, battery, and thermal limits. Use tracing, profiling, and measurement to debug and validate performance and power improvements, then collaborate to bring capabilities into production on real devices.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
OpenAI
OpenAI
15 hours ago

Operating Systems Engineer, On-Device Inference | Consumer Devices

āœ“ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 12 hours agoStatus: Live

Job Summary

Design and ship the operating system stack that enables reliable, responsive, and energy-efficient on-device AI inference. Build OS services and inference platform interfaces, integrate and optimize inference runtimes, adapt models to device constraints via quantization and memory optimization, and develop scheduling/resource policies for latency, memory, battery, and thermal limits. Use tracing, profiling, and measurement to debug and validate performance and power improvements, then collaborate to bring capabilities into production on real devices.
Location: San Francisco
Workplace: Onsite
Employment Type: Full time
Job Function: IT Operations (Systems/Network Admin)

Key Responsibilities

  • ā€¢Design and implement maintainable OS services, frameworks, and interfaces for inference execution, model loading and lifecycle, and resource management.
  • ā€¢Partner with researchers to fit models to device constraints using quantization, runtime integration, and memory optimization.
  • ā€¢Develop scheduling and resource policies to balance inference with other device activity while meeting latency, memory, battery, and thermal constraints.
  • ā€¢Develop and validate execution strategies for performance and power management that adapt to workload needs and changing device conditions.
  • ā€¢Use tracing, profiling, and structured debugging to investigate correctness, concurrency, performance, and reliability issues across models, runtimes, and OS components.

Pay and Benefits

Salary: USD 230,000 - 385,000 annually
Equity and Bonus:Equity

Key Requirements

  • ā€¢Substantial hands-on experience designing, developing, and debugging operating system components, system services, or performance-critical platform software.
  • ā€¢Proficiency in C++ for systems development, including concurrent programming, memory ownership, and resource lifetime management.
  • ā€¢Hands-on experience integrating or optimizing inference runtimes or machine learning workloads in resource-constrained environments.
  • ā€¢Strong understanding of scheduling and memory management, including how workloads compete for shared system resources.
  • ā€¢Ability to diagnose complex system behavior and deliver performance or power improvements using repeatable measurements.
Experience:On-device inferenceMachine learningEmbedded systemsConsumer devicesAI
Skills:DebuggingCross-disciplinary collaborationTechnical decision-makingPerformance optimizationMeasurement-driven improvement
Tech Stack:C++Rust

Company Brief

OpenAI
Develops and deploys advanced generative AI models (including ChatGPT and DALLĀ·E) and AI infrastructure, providing APIs and consumer products to accelerate safe AGI for broad benefit.
Industry: AI & Machine Learning
Company Size: Enterprise (1,001+ employees)
Revenue: USD 1B+
Growth: Scaleup
Valuation: Hectocorn (USD 100B+)
Funding: Series E+
Headquarters: San Francisco, United States
Founded: 2015
Glassdoor
Glassdoor: 4.4
WebsiteLinkedInGlassdoor