# Operating Systems Engineer, On-Device Inference | Consumer Devices
**Company:** [OpenAI](https://scaleengineer.com/companies/openai)
Operating Systems Engineer focused on on-device inference at OpenAI's Consumer Devices division, designing and developing the OS stack that enables advanced AI capabilities to run reliably, responsively, and efficiently on consumer hardware. You'll work across silicon, embedded systems, operating systems, and cloud services, partnering with researchers to integrate cutting-edge model capabilities while managing complex performance, power, and thermal constraints. This is a zero-to-one opportunity to build the platform infrastructure that brings powerful AI into everyday consumer products while optimizing for memory, compute, latency, and energy efficiency.
**Role:** Operating Systems Engineer
**Seniority:** Senior
**Locations:** San Francisco
**Salary:** 230000–385000 USD
[Apply](https://jobs.ashbyhq.com/openai/4a9774e2-6505-4cc2-92eb-22a8450aacdc)
Canonical: https://scaleengineer.com/jobs/openai/operating-systems-engineer-on-device-inference-consumer-devices
---
## Responsibilities

- Design and Implement Inference Platform: Architect and develop maintainable OS services, frameworks, and well-defined interfaces for inference execution, model loading and lifecycle management, and resource allocation. Create abstractions that enable seamless integration of inference workloads into the device OS while maintaining system stability and performance.
- Model Optimization and Constraint Management: Partner with ML researchers on quantization strategies, compression techniques, runtime integration, and memory optimization to fit advanced models within device memory, compute, and energy budgets. Evaluate model quality degradation and validate product behavior meets user expectations while respecting hardware constraints.
- System Resource Coordination and Scheduling: Develop intelligent scheduling algorithms and resource policies that balance inference workload execution with other device activities, ensuring system responsiveness while adhering to strict latency, memory, battery life, and thermal constraints. Implement dynamic resource allocation strategies that adapt to varying system conditions.
- Performance and Power Management Optimization: Develop, validate, and deploy execution strategies that adapt dynamically to workload characteristics, available system resources, and changing device thermal and power conditions. Build systems that maximize inference throughput while minimizing energy consumption and heat generation.
- Multi-Stack Debugging and Diagnostics: Apply advanced tracing, profiling, and structured debugging techniques to investigate correctness, concurrency issues, performance bottlenecks, and reliability problems spanning machine learning models, inference runtimes, and OS-level components. Develop tools and instrumentation to gain visibility across the entire inference stack.
- Performance Validation and Regression Testing: Build comprehensive diagnostic tools, system instrumentation, representative device workload scenarios, and automated test suites to demonstrate repeatable performance and energy improvements on physical hardware. Create mechanisms to catch regressions early and validate sustained performance under realistic usage patterns.
- Production Integration and Cross-Functional Collaboration: Work collaboratively with research, hardware, firmware, platform, and product engineering teams to translate emerging AI model capabilities into maintainable, production-ready systems. Drive solutions from early-stage exploration and prototyping through integration, testing, and reliable production deployment.

## Requirements

### education

- {"name":"Computer Science or Related Technical Degree","description":"Bachelor's degree in Computer Science, Computer Engineering, Electrical Engineering, or related technical field, or equivalent professional experience demonstrating mastery of computer systems fundamentals."}

### technical

- {"name":"OS Architecture and System Components","description":"Deep hands-on experience designing, developing, and debugging operating system components including system services, platform middleware, kernel interfaces, and performance-critical infrastructure. Proven ability to work with lower-level system abstractions and understand the full stack from hardware to application layer."}
- {"name":"C++ Systems Development","description":"Expert-level proficiency in C++ for systems programming, including advanced concurrent programming patterns, memory ownership models, RAII, move semantics, resource lifetime management, and performance optimization. Experience with multi-threaded systems and low-level memory management critical for OS-level code."}
- {"name":"On-Device Inference Integration","description":"Hands-on experience integrating, optimizing, or deploying inference runtimes and machine learning workloads in resource-constrained environments such as mobile devices, edge devices, or embedded systems. Understanding of constraints like limited memory, battery power, and computational resources."}
- {"name":"Scheduling and Resource Management","description":"Strong foundational knowledge of OS scheduling algorithms, memory management strategies, and how competing workloads negotiate for shared system resources. Experience implementing or optimizing resource allocation policies that balance multiple competing constraints."}
- {"name":"Performance Profiling and Analysis","description":"Demonstrated ability to diagnose complex system behavior using profiling tools, tracing frameworks, and performance analysis techniques. Track record of delivering quantifiable performance or power improvements supported by rigorous, repeatable measurements and validated on real hardware."}
- {"name":"Cross-Disciplinary Communication","description":"Strong ability to work effectively across engineering disciplines, translating abstract research and product requirements into concrete system requirements. Capability to articulate technical decisions, tradeoffs, and architectural rationale clearly to diverse audiences."}

### experience

- {"name":"Systems Programming at Scale","description":"3+ years of substantial professional experience developing systems-level software, including operating systems, runtime environments, middleware, or other performance-critical platform infrastructure in production environments."}
- {"name":"ML/AI Workload Optimization","description":"2+ years working with machine learning systems, neural network inference, or AI workload optimization, particularly in resource-constrained or mobile contexts. Understanding of model execution pipelines, tensor operations, and inference runtime characteristics."}
- {"name":"Hardware-Software Integration","description":"Experience working at the intersection of hardware and software, including exposure to hardware specifications, constraints, capabilities, and performance characteristics. Understanding of CPU, GPU, memory hierarchies, and device capabilities."}

## Skills

### required

- {"name":"C++","description":"Expert-level systems programming with C++, including concurrent programming, memory safety, and performance optimization for OS and runtime development"}
- {"name":"Operating Systems Design","description":"Deep understanding of OS architecture, system services, kernel interfaces, scheduling, memory management, and system-level performance characteristics"}
- {"name":"Performance Analysis and Profiling","description":"Advanced profiling, tracing, and performance measurement techniques to identify bottlenecks and optimize system behavior"}
- {"name":"Inference Runtime Integration","description":"Experience integrating machine learning inference runtimes into systems software and managing model execution in resource-constrained environments"}
- {"name":"Systems-Level Debugging","description":"Advanced debugging skills including concurrency issues, memory corruption, performance problems, and multi-component system interactions"}
- {"name":"Resource Scheduling and Management","description":"Knowledge of scheduling algorithms, resource allocation policies, and techniques for balancing competing system demands"}

### preferred

- {"name":"Rust","description":"Proficiency in Rust for systems programming, offering memory safety guarantees and performance characteristics suitable for OS and inference runtime development"}
- {"name":"End-to-End On-Device AI Product Delivery","description":"Shipped production experience with on-device inference from model adaptation and runtime integration through OS support and production debugging on consumer devices"}
- {"name":"Model Quantization and Compression","description":"Experience adapting models for deployment through quantization, pruning, knowledge distillation, or related compression techniques while balancing model quality and execution cost"}
- {"name":"Multi-Accelerator Inference Optimization","description":"Optimization experience across heterogeneous compute units including CPUs, GPUs, specialized neural processing units, or other accelerators, accounting for data movement, synchronization, and execution placement"}
- {"name":"Hardware Accelerator Integration","description":"Experience working with specialized hardware accelerators, DSPs, neural processing units, or other custom silicon for machine learning workloads"}
- {"name":"Battery and Thermal Management","description":"Understanding of power consumption profiling, battery life optimization, thermal management systems, and device-level power policies"}
- {"name":"Mobile or Embedded Systems","description":"Professional experience developing for mobile platforms (iOS, Android) or embedded systems with strict resource constraints similar to consumer device environments"}

## Tech stack

### tools

- {"name":"Performance Profilers","description":"CPU profilers, GPU profilers, memory profilers, and specialized tracing tools like perf, Instruments, and Android Profiler"}
- {"name":"Model Optimization Tools","description":"Model compression, quantization, and optimization frameworks including TensorFlow Model Optimization Toolkit and ONNX optimization utilities"}
- {"name":"Debuggers and Analysis","description":"GDB, LLDB, Valgrind, AddressSanitizer, ThreadSanitizer for multi-level debugging and dynamic analysis"}
- {"name":"Build Systems","description":"CMake, Bazel, or platform-specific build tools for managing complex systems code with multiple dependencies"}
- {"name":"Version Control","description":"Git and collaborative development workflows in large-scale codebases"}

### others

- {"name":"CUDA and GPU Computing","description":"GPU programming for inference optimization and accelerated computation on supported devices"}
- {"name":"Hardware Accelerator Programming","description":"Programming models and frameworks for specialized neural processing units, DSPs, or custom silicon"}
- {"name":"System Tracing and Profiling","description":"Low-level system instrumentation, kernel tracing, and performance analysis methodologies"}
- {"name":"Embedded Systems Architecture","description":"Understanding of embedded Linux, real-time systems, bootloaders, firmware, and hardware-software integration"}

### databases

- {"name":"Real-Time Telemetry Systems","description":"Time-series data collection and analysis for performance metrics, battery consumption, and thermal monitoring on devices"}

### languages

- {"name":"C++","description":"Primary language for systems programming, OS components, and performance-critical inference runtime development"}
- {"name":"Rust","description":"Increasingly used for systems programming to provide memory safety while maintaining performance, particularly for new OS components and runtime infrastructure"}
- {"name":"Python","description":"Used for model optimization, quantization scripts, simulation, testing frameworks, and research-to-production tooling"}
- {"name":"C","description":"Legacy systems integration and low-level hardware abstraction layer code"}

### frameworks

- {"name":"TensorFlow Lite","description":"Inference runtime optimized for on-device execution with support for quantization and model optimization"}
- {"name":"ONNX Runtime","description":"Cross-platform inference engine supporting multiple hardware backends and optimization profiles"}
- {"name":"Core ML","description":"Apple's machine learning framework for on-device inference on iOS and macOS platforms"}
- {"name":"Android Neural Networks API","description":"Android's neural network acceleration framework for hardware-accelerated inference"}

## Benefits

### benefits

- {"name":"Competitive Equity Compensation","description":"Participate in OpenAI's equity programs, aligning your success with company growth as a leader in AI research and deployment"}
- {"name":"Comprehensive Health Coverage","description":"Medical, dental, and vision insurance with competitive coverage for employees and dependents"}
- {"name":"401(k) Retirement Planning","description":"401(k) plan with company matching to support long-term financial planning"}
- {"name":"Generous Time Off","description":"Flexible paid time off, parental leave, and wellness days to support work-life balance"}
- {"name":"Professional Development","description":"Access to training, conference attendance, and continued learning opportunities to stay current with rapidly evolving AI and systems technologies"}
- {"name":"Collaborative Research Culture","description":"Work alongside world-class AI researchers and engineers on cutting-edge problems at the frontier of AI systems and consumer hardware integration"}
- {"name":"Mission-Driven Environment","description":"Contribute directly to OpenAI's mission of ensuring AGI benefits all of humanity through meaningful work on products that impact billions of people"}

## Compensation

- **max:** 280000
- **min:** 180000
- **currency:** USD
- **stockOptions:** true

## Interview process

### steps

- {"name":"Initial Screening Call","description":"Conversation with a recruiter to discuss your background, experience with on-device inference or systems programming, and interest in OpenAI's consumer devices mission"}
- {"name":"Technical Phone Screen","description":"Deep-dive with an OpenAI engineer covering systems programming fundamentals, OS concepts, inference optimization challenges, and approach to solving complex problems across software and hardware boundaries"}
- {"name":"Systems Design Interview","description":"Whiteboard-style discussion designing OS-level infrastructure for inference execution, discussing tradeoffs in scheduling policies, resource management, and performance optimization strategies"}
- {"name":"Performance Optimization Challenge","description":"Technical problem focused on profiling, analyzing, and optimizing a system with resource constraints similar to consumer devices, discussing measurement methodology and validation approaches"}
- {"name":"Cross-Functional Discussion","description":"Conversation with product or hardware engineers about translating research capabilities into shipped products and navigating tradeoffs across disciplines"}
- {"name":"Executive or Principal Engineer Interview","description":"Conversation with senior technical leadership about long-term vision for on-device AI, technical strategy, and your approach to solving novel problems at the research-product boundary"}

## Full description
## **About the Team**

OpenAI Consumer Devices is building the next generation of products that bring powerful AI into people’s everyday lives. Guided by OpenAI’s mission to ensure AGI benefits all of humanity, our team combines world-class researchers, engineers, designers, and operators who care deeply about creating useful, intuitive, and responsible technology. You’ll have the opportunity to work alongside exceptional people on ambitious, zero-to-one challenges at the intersection of hardware, software, and AI. This is a chance to help define an entirely new category of products—and shape how people experience AI in the future.

Our team works across silicon, embedded systems, operating systems, and cloud services to build reliable consumer devices and the novel platforms required to support them. We partner closely with research to bring advanced AI capabilities into the physical world.

## **About the Role**

As an Operating Systems Engineer focused on on-device inference, you will design, develop, and ship the OS stack that makes advanced AI capabilities reliable, responsive, and energy efficient on consumer devices.

Your work will span OS services and frameworks, inference runtime integration, model fitting, scheduling, and performance and power management. You’ll partner with research to adapt models to device constraints, make design decisions across the stack, and carry solutions from early exploration through integration and production.

### **In this role, you will:**

* **Build the inference platform:** Design and implement maintainable OS services, frameworks, and clear interfaces for inference execution, model loading and lifecycle, and resource management.
* **Fit models to device constraints:** Partner with researchers on quantization, runtime integration, and memory optimization to meet memory, compute, and energy budgets while evaluating model quality and product behavior.
* **Coordinate system resources:** Develop scheduling and resource policies that balance inference with other device activity, preserving responsiveness within latency, memory, battery, and thermal constraints.
* **Advance performance and power management:** Develop and validate execution strategies that adapt to workload needs, available resources, and changing device conditions.
* **Debug across the stack:** Use tracing, profiling, and structured debugging to investigate correctness, concurrency, performance, and reliability issues across models, inference runtimes, and OS components.
* **Measure and validate improvements:** Build diagnostic tools, instrumentation, representative device workloads, and automated tests to demonstrate repeatable performance and energy gains on physical devices, catch regressions, and validate sustained use.
* **Bring capabilities to production:** Collaborate with research, hardware, firmware, platform, and product engineering teams to turn emerging model capabilities into maintainable systems and reliable shipped features.

## **Minimum Qualifications**

* Substantial hands-on experience designing, developing, and debugging operating system components, system services, or performance-critical platform software.
* Proficiency in C++ for systems development, including concurrent programming, memory ownership, and resource lifetime management.
* Hands-on experience integrating or optimizing inference runtimes or machine learning workloads in resource-constrained environments.
* Strong understanding of scheduling, memory management, and how workloads compete for shared system resources.
* Experience diagnosing complex system behavior and delivering performance or power improvements supported by repeatable measurements.
* Ability to work across disciplines, translate research and product needs into system requirements, and explain technical decisions and tradeoffs clearly.

## **You might thrive in this role if you:**

* Have delivered end-to-end on-device inference in shipped products, from model adaptation and runtime integration through OS support and production debugging.
* Have adapted models for deployment through quantization, compression, or related techniques, balancing quality, execution cost, and memory requirements.
* Have optimized inference across CPUs, GPUs, or neural accelerators, accounting for data movement, synchronization, and execution placement.
* Are proficient in Rust for systems programming.
* Take ownership of complete solutions and follow problems across model, runtime, and operating system boundaries.
* Challenge assumptions, develop new approaches when existing techniques fall short, and use experiments and measurements to guide decisions.
* Work constructively across disciplines and make careful tradeoffs among model quality, performance, power, reliability, security, and maintainability.

**About OpenAI**

OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. We push the boundaries of the capabilities of AI systems and seek to safely deploy them to the world through our products. AI is an extremely powerful tool that must be created with safety and human needs at its core, and to achieve our mission, we must encompass and value the many different perspectives, voices, and experiences that form the full spectrum of humanity. 

We are an equal opportunity employer, and we do not discriminate on the basis of race, religion, color, national origin, sex, sexual orientation, age, veteran status, disability, genetic information, or other applicable legally protected characteristic. 

For additional information, please see [OpenAI’s Affirmative Action and Equal Employment Opportunity Policy Statement](https://cdn.openai.com/policies/eeo-policy-statement.pdf).

Background checks for applicants will be administered in accordance with applicable law, and qualified applicants with arrest or conviction records will be considered for employment consistent with those laws, including the San Francisco Fair Chance Ordinance, the Los Angeles County Fair Chance Ordinance for Employers, and the California Fair Chance Act, for US-based candidates. For unincorporated Los Angeles County workers: we reasonably believe that criminal history may have a direct, adverse and negative relationship with the following job duties, potentially resulting in the withdrawal of a conditional offer of employment: protect computer hardware entrusted to you from theft, loss or damage; return all computer hardware in your possession (including the data contained therein) upon termination of employment or end of assignment; and maintain the confidentiality of proprietary, confidential, and non-public information. In addition, job duties require access to secure and protected information technology systems and related data security obligations.

To notify OpenAI that you believe this job posting is non-compliant, please submit a report through [this form](https://form.asana.com/?d=57018692298241&k=5MqR40fZd7jlxVUh5J-UeA). No response will be provided to inquiries unrelated to job posting compliance.

We are committed to providing reasonable accommodations to applicants with disabilities, and requests can be made via this [link](https://form.asana.com/?k=bQ7w9h3iexRlicUdWRiwvg&d=57018692298241).

[OpenAI Global Applicant Privacy Policy](https://cdn.openai.com/policies/global-employee-and-contractor-privacy-policy.pdf)

At OpenAI, we believe artificial intelligence has the potential to help people solve immense global challenges, and we want the upside of AI to be widely shared. Join us in shaping the future of technology.