Senior Software Workload Optimization Engineer

NVIDIA•Seattle, WA
•Hybrid

About The Position

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 improves how effectively GPU systems perform useful work. The work may include reducing the GPU hours needed to evaluate models, with projects evolving as priorities and performance bottlenecks change. The role takes a systems-oriented approach to workloads: measure performance, identify what limits useful throughput, implement improvements, and validate results. Success means measurably reducing the GPU resources required to deliver useful results across workloads. The engineer partners with workload owners to understand requirements, test improvements, and help deploy solutions.

Requirements

  • Experience analyzing and improving the performance of compute-intensive software.
  • Bachelor’s degree or equivalent experience.
  • At least 5 years of relevant experience is stated; the posting also separately lists three or more years of relevant experience.
  • Ability to reason about and optimize parallelism strategies, including tensor, data, pipeline, context, and expert parallelism, to balance throughput, communication overhead, and GPU resource use.
  • Understanding of GPU architecture and factors affecting utilization and application performance.
  • Experience using profiling, benchmarking, and measurement to guide optimization decisions.
  • Ability to work independently, communicate findings clearly, and collaborate with researchers and engineers.

Nice To Haves

  • Experience optimizing AI training, inference, evaluation, or other large-scale GPU workloads.
  • Experience with GPU programming or machine learning frameworks and performance tools.
  • Experience improving workload scheduling, batching, data pipelines, or multi-GPU configurations.
  • Familiarity with collecting and interpreting GPU telemetry.
  • Experience with energy-proportional computing or performance optimization under power, energy, or thermal design power budgets.
  • Experience with model quantization or numerical methods.

Responsibilities

  • Investigate the performance of evaluation and other AI workloads across GPU systems.
  • Identify bottlenecks in computation, memory, communication, data movement, orchestration, and resource allocation.
  • Evaluate and improve parallelism configurations, including how work is distributed across GPUs and nodes.
  • Assess how effectively workloads use GPU capabilities, including tensor cores, and identify opportunities to improve utilization.
  • Implement and validate changes that reduce GPU hours per unit of useful work or increase throughput.
  • Design clear benchmarks and measurements that account for tradeoffs among throughput, latency, resource use, and result quality or correctness.
  • Partner with workload owners to understand requirements, test improvements, and help deploy solutions.
  • Independently prioritize and drive optimization projects from investigation through measurable results.
  • Investigate unfamiliar code and systems and work with code owners to deliver end-to-end optimizations.

Benefits

  • Equity
  • Benefits (unspecified)
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service