AI Computing Software Development Engineer, TensorRT-LLM

NVIDIA

Software engineer developing NVIDIA TensorRT-LLM inference software for GPU-accelerated AI. Optimizing LLM performance, kernels, runtimes, and deployment across platforms.

Posted 8/10/2026full-timeTaipei • 🇹🇼 TaiwanMid-LevelSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in developing and optimizing Large Language Model (LLM) inference software, with strong proficiency in Python and C/C++. Capable of collaborating across teams to enhance deep learning inference performance and architecture.

Highest-signal resume keywords

Python ProgrammingC/C++ ProgrammingDeep Learning FrameworksLarge Language Model InferenceGPU Programming

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Software DevelopmentSoftware DesignPerformance ModelingCode OptimizationDebuggingTest DesignInference AlgorithmsArchitectural KnowledgeRuntime FeaturesKernels Implementation

Soft Skills

Excellent Communication SkillsProactive Work Ethic

Tools & Technologies

TensorRT-LLMPyTorchHuggingFaceCUDAOpenCL

Industry Keywords

Artificial IntelligenceDeep LearningHigh-Performance ComputingLLM ArchitecturesInference Frameworks

Tech Stack

Tools & technologies

PythonPyTorch

About the role

Key responsibilities & impact

Craft and develop robust inference software scalable across multiple platforms for functionality and performance
Analyze and optimize Large Language Model (LLM) inference performance
Follow academic and industrial developments in artificial intelligence and feature-update TensorRT-LLM
Implement kernels and runtime features supporting new LLM models and inference algorithms
Provide feedback on architecture and hardware design and development
Collaborate across software, research, and product teams to guide deep learning inference direction

Requirements

What you’ll need

Master or higher degree in Computer Engineering, Computer Science, Applied Mathematics, or related computing-focused degree, or equivalent experience
3+ years of relevant software development experience
Excellent Python programming, software design, and software engineering skills
Awareness of current LLM architectures and LLM inference techniques
Experience with deep learning frameworks such as PyTorch and HuggingFace
Ability to work proactively and without supervision
Excellent written and oral communication skills in English
Prior experience with an LLM inference framework or a deep-learning compiler is preferred
Understanding of operations inside LLM inference frameworks or the end-to-end LLM inference workflow is preferred
Experience in performance modeling, profiling, debugging, and code optimization of DL/HPC/high-performance applications is preferred
Excellent C/C++ programming and software design skills, including debugging, performance analysis, and test design, are preferred
Architectural knowledge of CPU and GPU is preferred
GPU programming experience with CUDA or OpenCL is preferred

Benefits

Comp & perks

Competitive salaries
Generous benefits package
Equal opportunity employer
Diversity valued