Performance Software Intern, Deep Learning Libraries

NVIDIA

. Write highly tuned compute kernels to perform core deep learning operations, including matrix multiplies, MoE, and Attention .

Posted 9/23/2026full-timeShanghai • ChinaEntry LevelWebsite

Core Competencies

Role fit

Core Competencies

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

Demonstrates expertise in optimizing deep learning operations and performance tuning on NVIDIA GPUs, with a strong foundation in parallel programming and computer architecture. Proficient in software engineering best practices, including regression testing and CI/CD workflows.

Highest-signal resume keywords

CUDA GPU ProgrammingPerformance-Oriented Parallel ProgrammingDeep Learning Library Kernel TuningComputer Architecture UnderstandingAssembly Programming Experience

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

Deep Learning OperationsMatrix MultiplicationPerformance AnalysisDebuggingNumerical MethodsLinear AlgebraTuning AlgorithmsOptimized Code DevelopmentRegression TestingTest Design

Tools & Technologies

OpenMPPthreadsLLVMTVM Tensor ExpressionsTensorFlow MLIR

Industry Keywords

Deep LearningCompute KernelsCI/CDAssembly Code GenerationHardware Programming Model

Tech Stack

Tools & technologies

AssemblyTensorflow

About the role

Key responsibilities & impact

Write highly tuned compute kernels to perform core deep learning operations, including matrix multiplies, MoE, and Attention
Follow software engineering best practices, including regression testing and CI/CD flows
Collaborate with the Compiler team on generating optimal assembly code
Collaborate with deep learning training and inference performance teams to identify layers requiring optimization
Collaborate with hardware and architecture teams on the programming model for new deep learning hardware features
Develop optimized code to accelerate linear algebra and deep learning operations on NVIDIA GPUs
Tune parallel algorithms and analyze their performance

Requirements

What you’ll need

Pursuing Masters or PhD degree in Computer Science, Computer Engineering, Applied Math, or related field
Demonstrated strong programming and software design skills, including debugging, performance analysis, and test design
Experience with performance-oriented parallel programming, even if it’s not on GPUs (e.g. with OpenMP or pthreads)
Solid understanding of computer architecture and some experience with assembly programming
Ability to identify bottlenecks, optimize resource utilization, and improve throughput
Tuning deep learning library kernel code
CUDA GPU programming
Numerical methods and linear algebra
LLVM, TVM tensor expressions, or TensorFlow MLIR