NVIDIA seeks a Senior Systems Software Engineer to join its team as a technical expert in optimizing deep learning inference for autonomous vehicles and robotics on edge devices. This role involves addressing customer optimization challenges by analyzing and improving deep learning models directly with automotive OEMs and robotics partners, driving performance benchmarking efforts, evaluating emerging model architectures, and collaborating across teams to enhance platform capabilities. The engineer will also contribute to build reviews, develop internal roadmap priorities based on real-world data, and represent NVIDIA externally through conferences and partner events. Essential skills include expertise in deep learning model optimization, proficiency with GPU architecture and CUDA, comprehensive knowledge of contemporary DL architectures, and experience with embedded software development within power-limited environments. The position requires a master’s degree or equivalent experience and over 12 years in the industry, emphasizing hands-on technical collaboration to solve complex performance issues.
Skills
CUDA
TensorRT
TVM
MLIR
XLA
Python
C/C++
QNX
Linux
GPU
Deep Learning
Transformer Models
Vision-Language Models
Diffusion Models
State Space Models
Parallel Programming
Memory Management
Embedded Systems
CI/CD
MLPerf
What you'll do
Address customer and partner optimization challenges by analyzing and improving deep learning models on NVIDIA platforms.
Own performance benchmarking to achieve leading results on MLPerf Edge and industry benchmarks.
Evaluate emerging model architectures regarding compilation feasibility and performance on target SOCs.
Deliver TensorRT and compiler-stack solutions for edge devices in autonomous vehicles and robotics workloads.
Contribute to build reviews and develop internal roadmap priorities based on real customer workload patterns.
Represent NVIDIA externally by sharing deep learning optimization expertise at conferences and partner events.
What we're looking for
Over 12 years of industry experience, including at least 8 years specializing in deep learning model optimization and neural network compilation.
Expertise in evaluating modern DL architectures like transformers, vision-language models, diffusion/flow matching, and state space models on GPU and SOC.
Proficiency in CUDA, TensorRT, compiler IRs, and low-level performance optimization using heterogeneous computing.
Comprehensive knowledge of embedded operating system internals, memory management, C/C++, and parallel programming (e.g., CUDA).
Experience delivering production inference solutions within power-limited, latency-sensitive deployment environments for edge devices.
Demonstrated capability to collaborate directly with external partners and customers in a deep technical role, solving workload issues and providing optimized solutions.
Market check
Salary context
This
$224,000–$356,500
range sits above
100%
of similar postings on FindRole.
Peer median band
$140,000–$234,000
Median floor and ceiling across peers.
Typical midpoint (25–75%)
$147,625–$223,331
Middle half of comparable postings.
Based on 240 comparable postings.*
* 240 is the maximum number of comparable postings sampled.
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
802 open roles
on FindRole.
Listed pay typically runs
$184,000–$287,500
across 798 roles with salary data.