OpenAI•26 days ago
Software Engineer, AI Accelerator Runtime
Recruiter Fit Breakdown & Candid Summary
1
This is a highly specialized systems engineering role focused on the hardware-software boundary for custom AI accelerators.
2
Ideal candidates have deep experience in low-level systems programming (C++/Rust) and a strong background in driver, firmware, or runtime development.
3
Candidates without experience in hardware-software co-design, memory management, or cycle-accurate simulation will likely struggle.
4
This role is best suited for engineers who enjoy debugging complex concurrency issues across the full stack from silicon to software.
Role Responsibilities
- 1Design and implement low-level device runtime for custom AI silicon.
- 2Build kernel-launch scheduling, command submission, and dependency tracking systems.
- 3Manage device memory spaces, data movement, and virtual-to-physical mappings.
- 4Implement synchronization primitives, events, and barriers for efficient execution.
- 5Use cycle-accurate simulators to validate and performance-tune runtime behavior.
- 6Collaborate with architecture, compiler, and silicon teams to define hardware-software interfaces.
Skills Matrix
Must-Have Skills
C++(cpp)
Rust
Systems Programming
Concurrency
Memory Management
Device Drivers
Firmware
Hardware-Software Co-design
Nice-to-Have Skills
Cycle-accurate simulation
DMA(Direct Memory Access)
Performance Profiling
Compiler internals
Free Instant Match Check
Will an ATS filter reject your resume for this role?
Check your keyword match score, missing must-have skills, and formatting flags — before you apply.
Checking saved resume…
No signups. Free check in 3 seconds.
Ready to submit your application?
Apply directly on OpenAI's official job portal.