Senior AI Inference & Model Optimization Engineer

NVIDIA; Santa Clara (CA); On-site; USD 224,000 - 357,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is seeking a senior software engineer to advance inference optimization for generative AI models, including LLMs and diffusion models, within the TRT Model Optimizer ecosystem.

You will leverage the Torch 2.0 ecosystem (TorchDynamo, torch.export, torch.compile) to analyze graphs and implement high‑performance kernel techniques for automated deployment and scalable model support.

Qualifications

• Master's, PhD, or equivalent in CS/AI or related field.
• 8+ years in Deep Learning.
• Strong Python, PyTorch, and ML tools.
• Excellent software design, debugging, and testing.
• Strong communication and collaboration.

Responsibilities

• Design and optimize inference for LLMs and diffusion models.
• Develop high-performance kernels and automated deployment features.
• Collaborate across teams to scale model support and deployment.

Skills

Deep Learning

Python

PyTorch

Software Design

Algorithms

Communication

Independent Work

Education

Advanced Degree

Tools

TorchDynamo

torch.export

TorchCompile

CUDA

Job description

NVIDIA is seeking a senior software engineer to advance inference optimization for generative AI models, including LLMs and diffusion models, within the TRT Model Optimizer ecosystem.

You will leverage the Torch 2.0 ecosystem (TorchDynamo, torch.export, torch.compile) to analyze graphs and implement high‑performance kernel techniques for automated deployment and scalable model support.