below marketmost similar roles pay hereabove market
This role pays more than
50%
of similar roles. Most pay
$167,537–$235,750
— the blue band above.
At the midpoint, this role pays about
$197k
versus about
$202k
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 AI Frameworks Engineer joins the CUTLASS team to develop Pythonic CUTLASS, a domain-specific language designed to bring high-performance math primitives to the Python environment. You will bridge the gap between low-level hardware primitives and high-level developer productivity by designing APIs that prioritize user experience for GPU programming. Key responsibilities include developing robust compilation infrastructure featuring AST transformations and JIT-friendly execution to lower Pythonic descriptions into GPU machine code. You will also build production-grade delivery infrastructure, including package distribution via wheels and conda, while creating debugging tools and profiler integrations. The role requires proficiency in C++, Python, and foreign function interfaces, alongside experience in library development, compiler foundations like LLVM or MLIR, and GPU architecture using CUDA.
Design APIs that provide a native feel for developers using modern scientific computing and deep learning frameworks.
Develop robust compilation infrastructure including AST transformations and JIT-friendly execution to lower Pythonic descriptions into GPU machine code.
Create debugging tools, profiler integrations, and validation methodologies to simplify kernel development.
Build production-grade delivery infrastructure for the open-source community, including package distribution for wheels and conda.
Manage user-facing documentation and testing for the CUTLASS project.
Implement high-performance math primitives and GPU kernel delivery using C++ and Python.
What we're looking for
MS or PhD degree in Computer Science, Electrical Engineering, or related field (or equivalent experience).
At least 3+ years of relevant experience.
Strong proficiency in Python and C++, specifically regarding the design of Python extensions and foreign function interfaces (FFI).
Experience in library or framework development, with a focus on creating intuitive APIs for complex technical systems.
Deep understanding of the Python ecosystem’s delivery stack, including building, testing, and distributing high-performance compiled extensions.
Active maintainer status or significant contributions to high-performance open-source libraries, AI frameworks, or compiler projects (LLVM/MLIR) (preferred).
Understanding of compiler foundations, such as intermediate representations (IR), lowering passes, or AST manipulation (preferred).
Experience with GPU Architecture and parallel programming models (CUDA) (preferred).
PyTorch
Ray
Kubernetes
Python
C++
Go
Triton Inference Server
Docker
CI/CD
Helm
Kustomize
Distributed Systems
CUDA
RPC
Nsight
Model Serving
Observability
Logging
Tracing