below marketmost similar roles pay hereabove market
This role pays more than
99%
of similar roles. Most pay
$151,000–$222,625
— the blue band above.
At the midpoint, this role pays about
$290k
versus about
$187k
for comparable roles.
Based on 240 similar postings.
Employer
About Nvidia
Nvidia is a leading designer of graphics processing units (GPUs) and system-on-chip units, powering gaming, professional visualization, data centers, and artificial intelligence workloads. Industry: Semiconductors & AI Computing
Nvidia currently has
1623 open roles
on FindRole.
Listed pay typically runs
$184,000–$287,500
across 1110 roles with salary data.
The Senior Systems Software Engineer - Deep Learning Solutions joins a team focused on optimizing deep learning inference for autonomous vehicles and robotics on edge devices. This role involves analyzing model architectures at the operator level, performing kernel trace analysis to locate performance issues, and evaluating modern architectures like transformers, vision-language models, diffusion/flow matching, and state space models. The engineer will build and deploy inference solutions on Jetson, DRIVE, and GPU + ARM platforms while developing Proofs of Readiness for Torch-TRT and MLIR-TRT. Key technologies include CUDA, C/C++, TensorRT, MLIR, and knowledge of QNX/Linux. The work addresses the technical challenge of achieving low-latency, power-limited production inference for complex perception and planning stacks within the physical AI domain.
Analyze and debug deep learning models for automotive OEMs and robotics partners to improve performance on NVIDIA platforms.
Drive performance benchmarking efforts to achieve leading results on MLPerf Edge and other industry benchmarks.
Evaluate emerging DL architectures for compilation feasibility, memory footprint, and latency on target SOCs.
Build and deploy inference solutions on Jetson, DRIVE, and GPU+ARM platforms for autonomous vehicle and robotics workloads.
Develop Proofs of Readiness and collaborate with compiler teams on Torch-TRT and MLIR-TRT frameworks.
Identify performance issues through kernel trace analysis and model architecture review at the operator level.
Represent NVIDIA externally by sharing deep learning optimization expertise at conferences and partner events.
What we're looking for
Master’s degree or equivalent experience in Computer Science, Electrical Engineering, or a related field.
Over 12 years of industry experience, including at least 8 years specializing in deep learning model optimization, inference engineering, or neural network compilation.
Over 5 years of validated expertise in embedded/edge software delivering production inference solutions in power-limited, latency-sensitive environments.
Proficiency in reviewing model architectures at the operator/kernel level and comprehensive knowledge of transformers, vision encoders, and diffusion models.
Expert knowledge of GPU architecture fundamentals, CUDA, and low-level performance optimization using heterogeneous computing.
Experience with TensorRT, compiler IRs, or equivalent inference optimization toolchains.
Solid understanding of embedded operating system internals (QNX/Linux), memory management, C/C++, and parallel programming.
Experience with ML compiler frameworks (TVM, MLIR, XLA, Triton) or contributing to inference runtime development (preferred).
CUDA
C++
Python
Deep Learning
Distributed Computing
PyTorch
JAX
TensorRT
vLLM
Triton
XLA
NCCL
MPI
UCX
Kernel Optimization
Model Optimization
FP8
INT8
Generative AI
TensorRT
CUDA
Python
C++
Triton
PyTorch
ONNX
TensorRT-LLM
Deep Learning Inference
Linux
DriveOS
QNX
ISO 26262
Real-time Systems
Hypervisors
Virtualization