DL Inference Engineer — TensorRT Performance & Optimization

NVIDIA; California; On-site; USD 124,000 - 242,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is seeking a Deep Learning Software Engineer to optimize the performance of our TensorRT inference ecosystem. The role focuses on benchmarking, quantization, scheduling, memory management, and distributed inference to elevate Gen AI performance across NVIDIA accelerators.

You will work with PyTorch, JAX, TensorFlow and ONNX, contributing to TensorRT and related OSS projects, while collaborating with teams spanning automotive, robotics, and vision domains.

Qualifications

• Bachelors, Masters, PhD, or equivalent in CS/Engineering.
• 2 years of relevant software development experience.
• Strong C++, Python programming and software engineering skills.
• Experience with DL frameworks and inference libraries.
• 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

Software engineering

Education

Bachelor's or higher in CS/Engineering

Tools

PyTorch

JAX

TensorFlow

ONNX

TensorRT

vLLM

Torch-TensorRT

Job description

NVIDIA is seeking a Deep Learning Software Engineer to optimize the performance of our TensorRT inference ecosystem. The role focuses on benchmarking, quantization, scheduling, memory management, and distributed inference to elevate Gen AI performance across NVIDIA accelerators.

You will work with PyTorch, JAX, TensorFlow and ONNX, contributing to TensorRT and related OSS projects, while collaborating with teams spanning automotive, robotics, and vision domains.