below marketmost similar roles pay hereabove market
This role pays less than
66%
of similar roles. Most pay
$196,750–$241,750
— the blue band above.
At the midpoint, this role pays about
$197k
versus about
$219k
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
1626 open roles
on FindRole.
Listed pay typically runs
$184,000–$287,500
across 1115 roles with salary data.
Senior Software Engineer, GPU Code Generation for Machine Learning Inference joins the TensorRT team to advance high-performance AI inference on NVIDIA GPUs. This role focuses on accelerating generative AI models for local and enterprise deployments by solving complex problems in GPU code generation, just-in-time compilation, and inference optimization. You will design and implement efficient code generation techniques, develop compiler optimizations like operator fusion and dynamic scheduling, and profile workloads to identify bottlenecks. The position requires developing robust software in C++ and Python for tooling and performance analysis. Key technical requirements include proficiency in GPU architecture, parallel programming, and compiler infrastructure like MLIR. Candidates should possess experience with CUDA, Triton, or CUTLASS, and familiarity with TensorRT, PyTorch, or ONNX Runtime to improve generative AI inference performance.
What does a Software Engineer earn in California?
Median $214500 from 1223 postings across 76 companies.
Design and implement efficient GPU code generation techniques in TensorRT to balance performance and latency.
Develop compiler optimizations including operator fusion, dynamic scheduling, and specialization for various model shapes.
Profile workloads and analyze generated GPU code to identify and resolve performance bottlenecks.
Develop robust, maintainable software in C++ and Python for tooling, testing, and performance analysis.
Translate deep GPU architecture knowledge into efficient code generation for generative AI inference.
Validate numerical correctness and explain performance tradeoffs for high-performance inference software.
What we're looking for
BS, MS, or PhD in Computer Science, Computer Engineering, or a related field, or equivalent experience.
4+ years of relevant software development experience, including contributions to a substantial codebase or project.
Strong proficiency in C++ and experience building performance-critical software.
Understanding of GPU architecture and parallel programming concepts, including memory hierarchies, thread execution, synchronization, and resource utilization.
Ability to perform rigorous performance analysis and debugging to validate numerical correctness and explain performance tradeoffs.
Experience developing or optimizing GPU kernels using CUDA, Triton, CuTe DSL, CUTLASS, or other GPU programming languages (preferred).
Experience with MLIR compiler infrastructure, intermediate representations, lowering, optimization passes, and GPU code generation (preferred).
Familiarity with NVIDIA Tensor Core architecture, mixed-precision computation, quantization, or low-level GPU performance analysis using tools such as NVIDIA Nsight (preferred).
CUDA
Python
C++
Rust
TensorRT-LLM
vLLM
SGLang
Triton
PyTorch
NVIDIA Nsight Systems
CUTLASS
NCCL
Quantization
Distributed Systems
GPU Architecture
Model Parallelism
Speculative Decoding