Senior Staff Engineer - Infrastructure Systems
Runware · United States
Infrastructureremotestaff
At a glance
Highlights
- Own the GPU software baseline running on every fleet node end to end.
- Build self-healing detection that catches failing GPUs before customers do.
- Bring up new GPU generations from delivery to serving traffic in days.
What they offer
- Generous paid time off including vacation, sick days and public holidays
- Meaningful stock options
- Flexible hours outside core collaboration blocks
- Paid maternity, paternity and caregiver leave
- Twice-yearly company retreats
Ideal candidate
Veteran systems engineer who lives below the framework and still codes daily. You chase GPU failures to root cause and build automation that stops them recurring.
Requirements
- 12+ years building and operating systems software with production GPU software at scale
- Deep hands-on knowledge of NVIDIA stack including kernel driver, CUDA runtime and libraries, NVML, DCGM and Container Toolkit
- Proven record taking GPU failures to root cause across hardware, firmware, driver and runtime
- Experience with Blackwell hardware, NVLink and NVSwitch topologies and liquid-cooled racks
- Experience with multi-GPU execution via NCCL, GPUDirect and RDMA over RoCE or InfiniBand
- Familiarity with inference serving internals such as PyTorch, TensorRT-LLM, vLLM or SGLang
- remote policy
- remote-first
Lab profile
About Runware
High-performance GPU infrastructure and API for fast, scalable AI inference across models.
What they build
- Model API for image, video and LLM inference
- Serverless GPU platform for deploying AI models
- Dedicated inference capacity
Known for
- Fast real-time inference at scale
- Single flexible API across thousands of models
- Production-grade reliability and performance
- Lower cost and operational simplicity
Posted · Last seen