NVIDIA’s numerics team develops techniques to make large language models more efficient. The Senior Software Workload Optimization Engineer independently leads investigations into AI workloads and helps improve how effectively GPU systems perform useful work. The work may include reducing the GPU hours required to evaluate models and will evolve as priorities and bottlenecks change. The engineer analyzes workloads as systems: measuring performance, identifying limits to useful throughput, implementing improvements, and validating results. The role involves working with workload owners to understand requirements, test improvements, and support deployment. Success means measurably reducing GPU resources needed to deliver useful results across workloads. Expertise in quantization algorithms is not required.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
Job Type
Full-time
Career Level
Senior