TensorRT Performance DL Engineer

NVIDIA; Santa Clara (CA); On-site; USD 124,000 - 242,000; Full time

Benefits offered by this job

Equity compensation

Benefits package

Job summary

NVIDIA in Santa Clara, CA is seeking a Deep Learning Software Engineer focused on TensorRT performance. You will analyze and optimize inference pipelines, collaborate with teams across AI domains, and contribute to TensorRT, Torch-TensorRT, and related OSS projects to push GenAI performance.

The role requires strong C++ and Python skills, experience with PyTorch, TensorRT, and DL workloads, and a track record in performance analysis.

Qualifications

• Bachelor’s, Master’s, PhD or equivalent in CS/EE/AI.
• 2+ years of software development experience.
• Strong C++ and Python programming skills.
• Experience with DL frameworks (PyTorch, TensorFlow, ONNX) and inference libraries (TensorRT, TensorRT-LLM, vLLM, SGLang, FlashInfer).
• Experience with performance analysis and optimization.

Responsibilities

• Establish groundbreaking performance benchmarking methodologies and analysis workflows and identify performance issues and opportunities for NVIDIA’s inference ecosystem (e.g. TensorRT/TensorRT-EdgeLLM/Torch-TensorRT).
• Contribute features and code to NVIDIA/OSS inference frameworks including but not limited to TensorRT/TensorRT-EdgeLLM/Torch-TensorRT.
• Develop new model pipelines for NVIDIA’s inference ecosystem with optimized performance including but not limited to areas like quantization, scheduling, memory management, and distributed inference to set the gold standard for Gen AI performance.
• Work with cross-collaborative teams inside and outside of NVIDIA across generative AI, automotive, robotics, image understanding, and speech understanding to set directions and develop innovative inference solutions.
• Scale performance of deep learning models across different architectures and types of NVIDIA accelerators.

Skills

C++

Python

Education

Bachelor's degree in CS/EE/AI

Master's degree preferred

PhD in a related area

Tools

PyTorch

TensorFlow

ONNX

CUDA

Job description

NVIDIA in Santa Clara, CA is seeking a Deep Learning Software Engineer focused on TensorRT performance. You will analyze and optimize inference pipelines, collaborate with teams across AI domains, and contribute to TensorRT, Torch-TensorRT, and related OSS projects to push GenAI performance.

The role requires strong C++ and Python skills, experience with PyTorch, TensorRT, and DL workloads, and a track record in performance analysis.