Senior Software Engineer – TensorRT Edge-LLM

NVIDIA AI; Santa Clara (CA); On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

Equity

Health Insurance

Job summary

NVIDIA AI in Santa Clara is seeking a highly capable software engineer to advance an advanced inference framework using modern C++. The role focuses on extending TensorRT with autoregressive model serving capabilities and requires collaboration across CUDA, kernel libraries, compilers, and robotics teams to deliver high-performance, production-ready solutions.

The candidate should hold a BS/MS/PhD (or equivalent) and have at least four years of software development experience with a deep

Qualifications

• Candidates should have a BS, MS, PhD, or equivalent experience in a relevant field and at least 4 years of software development experience.
• A deep understanding of transformer models and proficiency in modern C++ are essential.

Responsibilities

• Develop and evolve a state-of-the-art inference framework in modern C++ that extends TensorRT with autoregressive model serving capabilities.
• Collaborate with teams across CUDA, kernel libraries, compilers, and robotics to deliver high-performance, production-ready solutions.

Skills

C++

TensorRT

LLM

VLM

GEMM

CUDA

Attention

MoE

KV Cache Management

Speculative Decoding

Quantization

Tensor Parallelism

Memory-Efficient Scheduling

Compiler Infrastructure

Robotics

Embedded AI

Education

BS/MS/PhD or equivalent

Job description

Develop and evolve a state-of-the-art inference framework in modern C++ that extends TensorRT with autoregressive model serving capabilities. Collaborate with teams across CUDA, kernel libraries, compilers, and robotics to deliver high-performance, production-ready solutions.

Requirements

Candidates should have a BS, MS, PhD, or equivalent experience in a relevant field and at least 4 years of software development experience. A deep understanding of transformer models and proficiency in modern C++ are essential.

Key Skills

C++, TensorRT, LLM, VLM, GEMM, CUDA, Attention, MoE, KV Cache Management, Speculative Decoding, Quantization, Tensor Parallelism, Memory-Efficient Scheduling, Compiler Infrastructure, Robotics, Embedded AI

Benefits

Equity, Health Insurance