NVIDIA 2027 New College Graduate: GPU Architecture Engineering - China

Job Title

NVIDIA 2027 New College Graduate — GPU Architecture Engineering (China)

Role Summary

Join NVIDIA's GPU Architecture team as a new college graduate to work on GPU and SoC architecture, performance, validation, and bring-up across the hardware and software stack.

Work includes modeling, simulation, verification, profiling, and cross-functional collaboration throughout the chip development lifecycle.

Experience Level

Entry-level — New college graduate expected to graduate in 2027.

Responsibilities

Typical responsibilities vary by team; examples below represent common duties for new college graduates in GPU architecture.

• Develop performance and functional models for GPU architectures and analyze graphics and compute pipelines.
• Build and enhance SoC performance simulators; capture, replay, and profile complex application workloads.
• Develop pre-silicon programming and test environments and support integration across architecture, hardware, and software teams.
• Create directed and constrained-random test plans; run and debug tests on functional simulators, RTL, emulators, and silicon.
• Explore GPU and memory-system architecture options and validate new features to improve performance and functionality.
• Profile, diagnose, and optimize system and application performance; develop tools and methodologies to improve analysis efficiency.
• Validate designs across models, RTL simulation, emulation, and silicon; support bring-up and post-silicon debug.

Requirements

Key technical skills and experience expected for applicants.

• Must-have: Proficiency in C/C++, Python, Linux, and object-oriented software development.
• Must-have: Understanding of computer systems, compilers, and assembly language.
• Must-have: Experience with performance or functional modeling, profiling, or trace-/execution-driven simulation.
• Must-have: GPU programming and debugging experience (CUDA preferred).
• Nice-to-have: Experience with SystemC or other system modeling tools.
• Nice-to-have: Exposure to ASIC design, RTL, verification, random-test development, or post-silicon validation.
• Nice-to-have: Experience developing deep learning models or optimizing AI workloads.

Education Requirements

Expected to graduate in 2027 with a Bachelor's, Master's, or PhD in Electrical Engineering, Computer Engineering, Computer Science, or a related technical field.

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.