2 days ago
Taipei, TaiwanEntry Level
Responsibilities
- Build and enhance high-performance LLM inference pipelines.
- Analyze and optimize LLM model execution, scalability, and memory usage.
- Deliver efficient multi-GPU model serving for agentic AI workloads in collaboration with framework and research teams.
- Improve the TensorRT compiler backend through graph transformations, code generation, operator fusion, and memory optimization.
- Collaborate with CUDA and hardware architecture teams to accelerate deep learning inference computations.
Requirements
- Master's or higher degree in Computer Science, Computer Engineering, Electrical Engineering, Applied Mathematics, or a related computing-focused degree, or equivalent experience.
- Excellent problem-solving ability, curiosity about modern AI systems, and passion for GPU computing and deep learning software performance.
- For TensorRT-LLM: strong Python programming, PyTorch experience, and understanding of LLM inference operations and GPU acceleration.
- For TensorRT Compiler: proficiency in C++ and experience with compiler or performance optimization.
Categories
About Nvidia
Nvidia designs and sells GPUs and accelerated computing platforms for data centers, AI/ML, graphics, gaming, and automotive, monetizing through hardware, software platforms (CUDA, AI frameworks), and systems like DGX and networking. Customers include cloud providers, enterprises, researchers, and OEMs. Founded in 1993 and headquartered in Santa Clara, it is a public company traded on NASDAQ under NVDA.