Senior Software Engineer - GPU Kernel Authoring & Optimization

Highlights

• Tune GPU kernels driving large-scale model serving at peak throughput.
• Lead MLPerf benchmarking to prove industry-leading inference performance.
• Turn kernel wins into end-to-end latency gains at massive scale.

What they offer

• Tuition Reimbursement
• Ability to Participate in Employee Stock Purchase Program (ESPP)
• Mental Wellness Benefits through Spring Health
• Family-Forming support provided by Carrot
• Paid Parental Leave
• Flexible, full-service childcare support with Kinside
• 401(k) with a generous employer match
• Flexible PTO
• Catered lunch each day in office and data center locations

Ideal candidate

A performance-obsessed owner with deep HPC background who lives for squeezing maximum throughput from hardware and translating low-level wins into reliable scale, while mentoring others and raising engineering standards.

Requirements

• 5+ years of experience building high-performance computing, GPU/accelerator software, or performance-critical systems
• Hands-on CUDA experience writing and optimizing custom kernels with fluency in CUDA programming and memory model
• Deep understanding of GPU architecture: tensor cores, warp/occupancy tuning, memory hierarchy and bandwidth, NVLink/PCIe, profiling with Nsight Compute/Systems
• Strong coding in C++ and Python for low-level, performance-sensitive code
• Familiarity with model-serving stacks (vLLM, TensorRT-LLM, llm-d, SGLang) and kernels that dominate inference cost
• Strong communicator comfortable collaborating with cross-functional teams and external partners