Senior ML Inference Engineer – TensorRT & LLMs

NVIDIA; Santa Clara (CA); On-site; USD 152,000 - 288,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is seeking talented engineers for the TensorRT team to advance the industry-leading deep learning inference software. You will design, develop and optimize TensorRT/TensorRT-LLM for diverse inference workloads across data centers, workstations and PCs.

The role requires strong C++, Python, and CUDA skills, plus experience with DL frameworks and compilers. You will collaborate with DL experts and GPU architects to influence HW/SW design in a fast-paced environment.

Qualifications

• BS/MS/PhD or equivalent experience in Computer Science or related field.
• 4+ years of software development on a large codebase or project.
• Strong proficiency in C++ (required), Rust or Python.
• Experience in developing Deep Learning frameworks, compilers, or system software.
• Excellent problem-solving and collaborative skills.

Responsibilities

• Design, develop and optimize TensorRT and TensorRT-LLM for inference applications.
• Develop software in C++, Python, and CUDA for deploying state-of-the-art LLMs and Generative AI models.
• Collaborate with DL experts and GPU architects to influence hardware and software design for inference.

Skills

C++

Rust

Python

CUDA

Education

BS in CS/CE

MS in CS/CE

PhD in CS/CE

Tools

TensorRT

PyTorch

JAX

Job description

NVIDIA is seeking talented engineers for the TensorRT team to advance the industry-leading deep learning inference software. You will design, develop and optimize TensorRT/TensorRT-LLM for diverse inference workloads across data centers, workstations and PCs.

The role requires strong C++, Python, and CUDA skills, plus experience with DL frameworks and compilers. You will collaborate with DL experts and GPU architects to influence HW/SW design in a fast-paced environment.