Deep Learning Performance Intern - 2027
NVIDIAJob Title
Deep Learning Performance Intern - 2027
Role Summary
Join NVIDIA's deep learning performance team in Shanghai to analyze and optimize deep learning workloads on GPU and accelerator architectures. The role supports performance modeling, benchmarking, bottleneck analysis, and feature evaluation for AI workloads including LLMs and generative models.
Experience Level
Entry-level internship suitable for current students or recent graduates (BSc/MS/PhD candidates commonly targeted).
Responsibilities
Key day-to-day activities include:
- Benchmark and analyze performance of machine learning / deep learning algorithms on GPU and NPU architectures.
- Develop performance models and produce workload projections across architectures.
- Identify architecture, software, and system-level performance bottlenecks and recommend optimizations.
- Explore and evaluate new hardware features and their impact on deep learning applications.
- Collaborate with engineers to optimize kernels and software stacks for generative AI and LLM workloads.
Requirements
Must-have technical skills and experience:
- Familiarity with GPU- or accelerator-based deep learning platforms and software stacks.
- Strong background in computer architecture.
- Familiarity with LLMs or generative AI algorithms and kernel optimization concepts.
- Experience or interest in system architecture design and performance optimization.
- Familiarity with machine learning and deep learning frameworks.
Nice-to-have:
- Experience with performance benchmarking, profiling tools, and kernel-level optimization (e.g., profiling CUDA or similar environments).
Education Requirements
BSc, MS, or PhD in Computer Science, Electrical Engineering, Mathematics, or a related technical discipline.
About the Company
Company: NVIDIA
Headquarters: Santa Clara, California, USA
NVIDIA is a global leader in accelerated computing, renowned for its innovative solutions in AI and digital twins that transform diverse industries. The company specializes in networking technologies, providing end-to-end InfiniBand and Ethernet solutions for servers and storage that optimize performance and scalability. NVIDIA serves sectors such as high-performance computing, enterprise data centers, and cloud computing, constantly reinventing its products and services to stay ahead in the market.
