CareerPlan

Staff GPU Performance / Kernel Engineer

USAFull-time2026-10-07 → 2026-11-18
Hybrid

Core

Profile, analyze, and optimize GPU kernels to improve latency, throughput, and utilization for large-scale AI workloads.

Role type

Staff GPU Performance / Kernel Engineer

Builds

Optimized GPU infrastructure for training and inference environments

Domain

AI infrastructure and GPU computing

Deliverable

production ML models

Required skills

GPU kernel development, CUDA, ROCm, GPU architecture, memory hierarchy, parallel computing, performance profiling, systems programming

Preferred skills

NVIDIA and AMD GPU optimization, GPU compiler technologies, low-level systems performance, Nsight Systems, Nsight Compute

Technologies

CUDA, ROCm, Nsight Systems, Nsight Compute

Responsibilities

Analyze and optimize GPU kernels, identify data-plane bottlenecks, tune performance-critical workloads, develop benchmarking methodologies, evaluate emerging GPU technologies, improve fleet efficiency and scalability

Seniority

Staff, hands-on IC