NVIDIA
Senior Software Engineer, GPU Code Generation for Machine Learning Inference
$152K–$288K
US, CA, Santa Clara +1 · Senior · Full-time · Posted Oct 21, 2026
- Location
- US, CA, Santa Clara
US, CA, Remote - Experience
- 4+ years of relevant software development experience.
- Education
- BS, MS, or PhD in Computer Science, Computer Engineering, or a related field, or equivalent experience.
About the job
Develop GPU code generation and compiler optimizations for TensorRT to improve generative AI inference performance across models and NVIDIA hardware.
What you'll do
- Design code generation techniques that balance runtime performance, compilation overhead, and startup latency.
- Develop compiler optimizations, profile workloads, and analyze generated GPU code to guide compiler and runtime improvements.
- Build C++ software and Python tooling for testing and performance analysis, collaborating across GPU and AI teams.
What they ask 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, including memory hierarchies, thread execution, synchronization, and resource utilization.
Nice to have
- GPU kernel development or optimization experience using CUDA, Triton, CuTe DSL, CUTLASS, or other GPU programming languages; or MLIR compiler experience.
- Familiarity with NVIDIA Tensor Core architecture, mixed-precision computation, quantization, NVIDIA Nsight, or inference frameworks.
Pay
152,000 USD - 241,500 USD (base salary, Level 3); 184,000 USD - 287,500 USD (base salary, Level 4)
Tools
TensorRT, C++, Python, CUDA, Triton, CuTe DSL, CUTLASS, MLIR
AI focus
Develop and optimize GPU software for generative AI model inference.
Model-written summary · the original posting is authoritative