This role may have closed.
Listings older than 30 days are deprioritized in search. The link to the source is still below in case the posting is still open. For active openings, see similar jobs.
Rebellions
NPU Software Engineer - Runtime
Seoul, South KoreaPosted 4 months ago
What you'd do
- Design and implement RBLN runtime module interfacing with compiler and driver components.
- Architect native PyTorch execution support including torch.compile integration for NPU acceleration.
- Design and implement user-facing profiler providing performance insights in RBLN SDK.
What they want
- 5+ years software engineering experience in ML frameworks,inference runtimes,or AI accelerator toolchains.
- Bachelor's degree or higher in Computer Science,Electrical Engineering,or related field.
- Strong proficiency in C++ and Python.
Nice to have
- Practical experience with AI accelerator runtimes and driver APIs.
- Direct contribution or production experience with PyTorch,vLLM,SGLang,TensorRT,TensorRT-LLM.
- Understanding of torch.compile and graph optimizations.
Seoulstart's read
- Visa tier (likely)
- E-7 specialty / professional (likely)
- Korean language
- Korean not required
- English friendliness
- High: JD in English, foreign-friendly signals