below marketmost similar roles pay hereabove market
This role pays more than
92%
of similar roles. Most pay
$152,955–$207,337
— the blue band above.
At the midpoint, this role pays about
$236k
versus about
$180k
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 Software Engineer - NVIDIA Warp joins the team developing Warp, a framework providing Python productivity for high-performance simulation, scientific computing, and differentiable programming on CPUs and NVIDIA GPUs. This role involves owning the end-to-end technical path for adopting Warp in computational applications, including native C++ and CUDA changes, production integration, and validation. You will turn new CUDA features into supported Warp functionality to improve performance and portability across accelerated-computing platforms. Key responsibilities include partnering with internal engineering teams to integrate Warp into software like ALCHEMI and PhysicsNeMo, while selecting CUDA-X libraries to address technical gaps. You will design APIs and reusable building blocks for simulation, optimization, and AI workloads, utilizing C++, CUDA, and Python to solve complex computational physics and engineering problems.
What does a Software Engineer earn in California?
Median $214500 from 1193 postings across 76 companies.
Own the end-to-end technical path for adopting Warp in computational applications from C++ and CUDA changes to production.
Convert new CUDA features and programming models into supported Warp functionality to improve performance and portability.
Integrate Warp into internal software products like ALCHEMI, BioNeMo, and PhysicsNeMo to resolve technical barriers.
Select and integrate CUDA-X libraries and other computing technologies into consistent Python and native APIs.
Design and implement new APIs, programming abstractions, and reusable building blocks for simulation and AI workloads.
Optimize performance-critical CUDA C++ software by diagnosing issues involving parallel execution and GPU memory behavior.
Maintain production-quality open-source software including testing, CI/CD, packaging, and release practices.
What we're looking for
Hold a BS, MS, or PhD in a relevant computational engineering field or equivalent experience.
Have 8+ years of relevant software development experience in industry or academic research.
Possess significant experience building, debugging, profiling, and optimizing performance-critical CUDA C++ software for NVIDIA GPUs.
Have substantial experience building and supporting computational software involving numerical methods, model validation, or scientific data pipelines.
Own framework integrations from prototype through production across multiple software projects (preferred).
Have hands-on experience designing and optimizing software for systems combining CPUs, GPUs, memory, and high-speed interconnects (preferred).
Have experience defining and evolving Python GPU programming systems across programming models, compilers, runtimes, and kernel libraries (preferred).
Have experience shipping and maintaining production-quality open-source software within a large distributed team (preferred).
C
C++
CUDA
Vulkan
DirectX
OpenGL
NvMedia
H.264
HEVC
AV1
Multi-threaded programming
Video Codec SDK
V4L2
OS internals
Kernel-mode drivers
Telemetry
Adaptive bit-rate
DLSS
RTX
C
RISC-V
Ada
SPARK
Firmware Development
Embedded Systems
PCIe
I2C
I3C
SPI
SMBus
MCTP
PLDM
Hardware Roots of Trust
Cryptographic Hardware Accelerators
Assembly
Debugging