Senior Staff Engineer – Infrastructure Systems

Job not on LinkedIn

🔥 0 minutes ago

🏄 California – Remote

🏄 California – Remote

⏰ Full Time

🟠 Senior

👷 Infrastructure Engineer

👻 Ghost score 25%

What it means: the chance that no one is really hiring for this job.How to read it: 60% or higher means we think this is a ghost. Lower scores are less of a worry.Why this score:

• Just posted.
• Jobs at this company usually fill in 21 days.
• 24 open roles for a team of 15.
• No salary listed.

Apply Now

Check your resume score

Customize resume + cover letter

Find Similar Remote Jobs

☆ Save☑️ Mark as applied❌ Hide

Report problem

Runware

WebsiteLinkedInAll Job Openings

11 - 50 employees

Founded 2023

🤖 Artificial Intelligence

🔌 API

📱 Media

Artificial Intelligence • API • Media

Runware is a flexible generative AI platform that specializes in high-quality media creation for images and videos through an affordable and fast API. It is capable of advanced tasks such as image generation, video inference, upscaling, and background removal, making it an essential tool for developers seeking to enhance their projects with AI technology. Powered by a custom Sonic Inference Engine™ and renewable energy, Runware ensures quick and efficient media generation without requiring complex infrastructure or machine learning expertise.

📋 Description

• Own the GPU software baseline across kernel, NVIDIA driver, firmware, CUDA runtime and libraries, and container toolkit • Qualify driver and CUDA releases across GPU generations, frameworks, and model families • Maintain compatibility matrices and identify correctness, performance, and memory regressions • Root-cause GPU failures including Xid errors, CUDA errors, cuBLAS failures, out-of-memory issues, fragmentation, and GPUs falling off the bus • Build GPU acceptance, burn-in, diagnostics, memory, interconnect, and real-workload tests • Make GPU health visible and self-healing using telemetry from DCGM, drivers, kernel logs, and BMC • Automate GPU fault classification, node draining, resets, and replacement workflows • Own GPU workload exposure through container runtime, device plugins, GPU Operator, MIG, sharing policies, and tenant isolation • Bring up new GPU generations and pods with hardware and node operations teams • Validate drivers, firmware, NVLink, and NVSwitch and automate future bring-up • Benchmark image, video, audio, and LLM inference across GPU generations and software stacks • Feed performance results into placement, pricing, and hardware purchasing decisions • Work with NVIDIA and upstream projects on reproducible driver and firmware bugs and open-source fixes • Use AI agents for log and Xid triage, test generation, release qualification, and runbook automation • Collaborate with node operations, Managed Kubernetes, inference performance, and Sonic Inference Engine teams

🎯 Requirements

• 12+ years building and operating systems software, including several years with GPU software running in production at scale • Deep hands-on knowledge of the NVIDIA software stack: kernel driver and modules, CUDA runtime and libraries, NVML, DCGM, Container Toolkit, and version interactions • Experience root-causing GPU failures across hardware, firmware, driver, runtime, and application layers • Knowledge of Xid errors, ECC and row remapping, PCIe and NVLink errors, thermal faults, and memory faults • Strong Linux internals knowledge: kernel, device drivers and modules, PCIe, NUMA, IOMMU, cgroups, containers, perf, eBPF, and ftrace • Daily coding experience • Fluent in Python and at least one systems language: C, C++, Rust, or Go • Comfortable using CUDA to write tests or reproduce bugs • Experience running GPUs under Kubernetes and on bare metal, including device plugins, GPU Operator, MIG, image builds, and large-scale provisioning • Working knowledge of GPU inference frameworks including PyTorch, TensorRT, and ONNX Runtime • Knowledge of memory allocation, compilation and caches, and multi-GPU execution • Clear technical writing for design documents, postmortems, and ticket updates • Daily use of AI tools to accelerate output • Comfortable owning outcomes in a fast-moving, ambiguous environment • Nice to have: GPU driver, CUDA library, or GPU system software experience at a GPU vendor, cloud provider, or HPC centre • Nice to have: Blackwell hardware, NVLink/NVSwitch topologies, and liquid-cooled racks • Nice to have: NCCL, GPUDirect, RDMA over RoCE or InfiniBand • Nice to have: Firmware qualification across BIOS, BMC, NIC, and GPU • Nice to have: Inference serving internals including TensorRT-LLM, vLLM, SGLang, or custom diffusion/video pipelines • Nice to have: AMD or custom accelerator software stacks • Nice to have: An open-source project used in production • Nice to have: Multi-tenant isolation and confidential computing on shared GPU hardware • Nice to have: Experience running a 24x7 service with published service levels

🏖️ Benefits

• Remote-first work arrangement • In-person company retreats twice a year • Core collaboration hours with flexible hours outside them • Flexible schedule • Downtime after major release pushes • Generous paid time off: vacation, sick days, public holidays • Meaningful stock options • Paid maternity, paternity, and caregiver leave

📊 Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Upload Resume