← All roles

Senior Systems Software Engineer - Deep Learning Solutions

NVIDIA· Engineer, Sys SW
Apply on company site
Santa Clara, CA$224k - $356.5kfull-timePosted 7mo ago

About the role

Senior Systems Software Engineer focused on optimizing deep learning inference for autonomous vehicles and robotics on edge devices, combining model-architecture analysis, kernel trace techniques, and collaboration with compiler, runtime, and hardware teams to deliver edge inference solutions.

Responsibilities

  • Address customer and partner optimization challenges: engage with automotive OEMs and robotics associates to analyze, debug, and improve deep learning models on NVIDIA platforms.
  • Own performance benchmarking: drive MLPerf Edge and industry benchmarks, define methodology, ensure reproducibility, and derive optimization priorities.
  • Evaluate emerging model architectures: investigate DL architectures regarding compilation feasibility, memory footprint, and latency on target SOCs.
  • Collaborate across teams: work with compiler, runtime, and hardware groups to link model-level insight with platform capabilities.
  • Contribute to build reviews and help develop internal roadmap priorities based on customer workload patterns.
  • Represent NVIDIA externally: share optimization expertise at conferences, webinars, and partner events; bring back insights to the team.
  • Deliver TensorRT and compiler-stack solutions for edge: build/deploy inference on Jetson, DRIVE, and GPU+ARM platforms; develop PORs; collaborate on Torch-TRT, MLIR-TRT to bridge performance gaps.

Qualifications

  • Master’s degree or equivalent experience in Computer Science, Electrical Engineering, or related field.
  • Over 12 years in industry, including at least 8 years in deep learning model optimization, inference engineering, or neural network compilation.
  • Over 5 years of validated expertise in embedded/edge software with production inference experience in power-limited, latency-sensitive environments.
  • Knowledge of contemporary DL architectures: transformers, attention variants, ViT, multi-modal/vision-language models, diffusion and/or state space models.
  • Expert knowledge of GPU architecture fundamentals, CUDA, and low-level performance optimization; experience with TensorRT, compiler IRs, or equivalent inference toolchains.
  • Solid understanding of embedded OS internals (QNX/Linux), memory management, C/C++, and embedded/system software concepts.
  • Background in parallel programming (CUDA, OpenMP) and memory hierarchy, data movement, compute utilization.
  • Ability to collaborate with external partners/customers in a deep technical role to solve workload issues.

Skills

Required:DL model optimizationGPU/CPU low-level optimizationTensorRT / compiler toolchainsEmbedded/edge softwareC/C++

Benefits

  • equity
  • benefits (see company benefits page)
Last updated Oct 16, 2026. Interested? Apply on the company site.

About NVIDIA

World Leader in AI Computing

NVIDIA invents the GPU and drives advances in AI, HPC, gaming, creative design, autonomous vehicles, and robotics.

AIautonomous vehiclesgaminggpugraphics cardhigh performance computingliquid-ai-recruiting-targetllm
Company profileWebsite

More open roles at NVIDIA