NVIDIA
Senior Deep Learning Software Engineer, Inference
$184K–$356K
US, CA, Santa Clara +1 · Senior · Full-time · Posted Sep 10, 2026
- Location
- US, CA, Santa Clara
US, Remote - Experience
- 6+ years of relevant software development experience.
- Education
- Master's or PhD or equivalent experience in a relevant field (Computer Engineering, Computer Science, EECS, AI).
About the job
Develop and optimize GPU-accelerated deep learning inference software and model-serving platforms for LLMs and other Generative AI applications.
What you'll do
- Optimize and tune deep learning model performance across NVIDIA accelerators and architectures.
- Contribute features and code to inference libraries and solutions, including vLLM, SGLang, and FlashInfer.
- Collaborate with framework and library teams to implement inference optimizations and algorithms.
What they ask for
- Master's, PhD, or equivalent experience in a relevant field.
- 6+ years of relevant software development experience.
- Excellent C/C++ programming and software design skills.
Nice to have
- Python experience; software Agile skills.
- Experience with production deep learning model training, deployment, or inference optimization; performance profiling or GPU/CPU architecture knowledge.
Pay
184,000 USD - 287,500 USD (base salary, Level 4); 224,000 USD - 356,500 USD (base salary, Level 5)
Tools
SGLang, vLLM, FlashInfer, CUTLASS, OAI Triton, NCCL, CUDA
AI focus
Optimize and serve LLM, multimodal, and Generative AI models; implement algorithms and improve inference performance across NVIDIA accelerators.
Model-written summary · the original posting is authoritative