← All roles

GPU Architecture Engineer – New College Grad

NVIDIA· Engineer, Sys SW
Apply on company site
Hybrid (Shanghai), Hybrid (Beijing), Hybrid (Shenzhen)full-timePosted 2mo ago

About the role

NVIDIA seeks 2027 New College Graduates for GPU Architecture roles in China. Opportunities span modeling, performance analysis, SoC simulation, functional validation, verification, memory-system exploration, profiling, and bring-up across the chip development lifecycle. Must be a 2027 graduate in a related engineering field with strong software/hardware skills and AI workload optimization experience.

Responsibilities

  • GPU Architecture Modeling and Performance Analysis: conduct quantitative studies, develop performance and functional models, analyze graphics and parallel-compute pipelines, identify bottlenecks, propose architectural improvements.
  • SoC Performance Simulation and Workload Analysis: build/enhance performance simulators and modeling frameworks, capture/replay/profile real-world workloads, evaluate current and next-generation SoC performance across use cases.
  • GPU/System Functional Validation Platform Development: develop pre-silicon programming and test environments for next-generation GPU and system features, collaborate across architecture, hardware, and software teams.
  • GPU Functional Verification and Test Generation: create directed and constrained-random test plans with strong coverage, generate/run/debug tests across simulators, RTL, emulators, and post-silicon platforms.
  • GPU and Memory-System Architecture Exploration: explore novel GPU, processing, storage, and memory-system capabilities, validate features with architects, improve performance/functionality/test coverage.
  • Performance Profiling, Debugging, and Optimization: profile system/application behavior, diagnose bottlenecks, develop tools/methodologies to improve analysis and application performance.
  • Simulation, Emulation, and Silicon Bring-Up: validate designs from architectural models to real silicon, debug issues before/after product release.

Qualifications

  • Expected to graduate in 2027 with a Bachelor's, Master's, or PhD in Electrical Engineering, Computer Engineering, or a related field
  • Computer Architecture, GPU Architecture, Microprocessor Design, or Memory Systems
  • C/C++, Python, Linux, and object-oriented software development
  • GPU programming and debugging, including CUDA
  • Performance/functional modeling, profiling, trace-driven or execution-driven simulation
  • Computer systems, compilers, assembly language, and system modeling tools such as SystemC
  • ASIC design, verification, RTL, random-test development, or post-silicon validation
  • Deep learning model development or AI workload optimization

Skills

Required:C/C++PythonLinuxCUDA
Nice to have:SystemCASIC/RTL/verification
Last updated Aug 21, 2026. Interested? Apply on the company site.

About NVIDIA

World Leader in AI Computing

NVIDIA invents the GPU and drives advances in AI, HPC, gaming, creative design, autonomous vehicles, and robotics.

AIautonomous vehiclesgaminggpugraphics cardhigh performance computingliquid-ai-recruiting-targetllm
Company profileWebsite

More open roles at NVIDIA