Software Engineer, AI Accelerator Runtime
Build the low-level runtime for a custom AI accelerator, including kernel scheduling, device memory management, synchronization, and hardware-software interfaces. The role requires strong systems programming experience and expertise in concurrency, memory semantics, simulation, and performance debugging.
About the job
Responsibilities
- Design and implement the low-level device runtime for OpenAI custom silicon.
- Build kernel-launch scheduling, command submission, queueing, dependency tracking, and completion handling.
- Manage device memory spaces, allocation, virtual-to-physical mappings, data movement, and lifetimes across concurrent workloads.
- Implement synchronization primitives, events, barriers, streams, and ordering guarantees.
- Define interfaces between the runtime, drivers, firmware, compiler-generated code, kernels, and higher-level execution systems.
- Use event-based, cycle-accurate simulators to develop, validate, debug, and tune runtime behavior before and after silicon availability.
- Diagnose concurrency, memory-ordering, deadlock, race, correctness, and performance issues across software and hardware boundaries.
- Build tests, tracing, profiling, observability, and reproducible workloads for runtime correctness and performance.
- Partner with architecture and silicon teams on hardware-software interface improvements.
Requirements
- Strong low-level systems programming experience in C, C++, Rust, or comparable environments.
- Experience building runtimes, drivers, firmware, operating-system components, accelerator software, or adjacent systems infrastructure.
- Understanding of concurrency, synchronization, asynchronous execution, queues, events, and memory-ordering semantics.
- Understanding of memory management, address spaces, DMA, caching, coherency, and hardware-software interfaces.
- Hands-on experience with event-based, cycle-accurate simulators or related architectural and performance models.
- Ability to reason quantitatively about scheduling, latency, throughput, utilization, contention, and resource tradeoffs.
- Skilled at debugging issues spanning software abstractions, device interfaces, and hardware behavior.
- Ability to work across compiler, kernel, architecture, verification, firmware, and silicon teams.
Additional Information
- Candidates may need to meet legal status requirements under U.S. export control laws and regulations.
Skills
C, C++, Rust, Concurrency, Synchronization, Dma, Caching, Memory Management, Operating Systems, Device Drivers, Firmware, Cycle-Accurate Simulation, Profiling, Virtual Memory
Similar jobs
Embedded Engineering jobs
OpenAI
San Francisco, CA
Leads systems software bringup and validation for new AI silicon, developing diagnostics, automation, observability, and stress infrastructure from first power-on through integrated model execution. The role requires low-level programming, computer architecture knowledge, hardware-software debugging, and cross-functional technical leadership.
OpenAI
San Francisco, CA
Build and harden OS foundations for AI consumer devices, spanning kernel, services, security, performance, and application interfaces. Requires strong systems programming in C/C++, kernel experience, and debugging skills.
Applied Intuition
Sunnyvale, CA
Develops real-time perception, sensor-control, and fusion software for heterogeneous autonomous vehicle platforms, integrating ML algorithms across sensors and embedded systems. Requires advanced engineering education or 5+ years of relevant experience, multi-modal sensing expertise, Linux/Docker proficiency, and U.S. security-clearance eligibility.
Zoox
Foster City, CA
Develops operating-system platforms, device drivers, and infrastructure for autonomous-vehicle robotics systems. The role requires 4+ years of production software experience, strong Linux internals expertise, and proficiency in C/C++ plus scripting languages.
Applied Intuition
Sunnyvale, CA
Develops reliable embedded software and custom device solutions, integrating vendor components, sensors, operating systems, and communication interfaces. Requires a bachelor's degree and at least three years of relevant experience with C/C++, embedded Linux, debugging, and CI/CD tools.