3 days ago
Shanghai, ChinaIntern
Responsibilities
- Test AI agents and end-to-end agentic workflows across NVIDIA GPU platforms.
- Validate models across inference runtimes, model formats, precision and quantization settings, and hardware/software configurations.
- Design and execute functional, integration, end-to-end, reliability, and performance tests.
- Develop automated tests and evaluation frameworks for reasoning, tool use, multi-turn interactions, memory, and retrieval.
- Use AI development tools to improve test planning, case development, execution, analysis, and automation.
- Collaborate with development teams on issue triage, root-cause analysis, fix verification, and test coverage improvements.
Requirements
- Currently pursuing a master’s degree in Computer Science, Computer Engineering, Electrical Engineering, or a related field.
- Proficiency in Python and shell scripting, with strong software development potential.
- Hands-on experience downloading, configuring, and running open-source models, including models from Hugging Face, using at least one local inference runtime or framework.
- Experience using AI development tools across the end-to-end QA workflow.
- Knowledge of Linux, software development, and testing methodologies.
- Fluent written and spoken English with strong problem-solving, communication, and interpersonal skills.
- Experience with LLM applications, AI agents, agentic workflows, AI evaluation or test automation frameworks, RAG, tool calling, prompt engineering, or multi-agent systems is preferred.
- Experience with Docker, Kubernetes, OpenStack, NVIDIA GPU hardware, CUDA, parallel programming, or evaluating quantized and optimized models on workstation, embedded, or edge GPU platforms is preferred.
Benefits
- Full-time, on-site work five days per week for one year.
- Supportive and collaborative environment focused on innovation and learning.
Tech Stack
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.