The NVIDIA SOC group is looking for ASIC verification/infrastructures and methodologies interns. In this position, you will take part in all stages to design modern complex GPU/Tegra chips with state-of-art feature and flows, you will work directly with different global teams, as Arch/SW, ASIC Design/Verification, SOCD/Clocks/SysASIC, DFT and Physical Design teams. Additionally, you will be involved in defining and creating infrastructures and methodologies that create more efficient and flexible SOCs in future.

What you’ll be doing:

• Participate in chip top integration and assembly,Engage in design/verification work of system-level units

• Optimize composing/verification flow, processes, and methodologies, Develop new tools and flows to improve efficiency and quality

• Participate in developing intelligent application systems based on Large Language Models (LLMs) for Chip Design, including conversational systems, intelligent assistants, and knowledge Q&A systems

• Learn and implement RAG (Retrieval-Augmented Generation) systems, assist in optimizing information retrieval accuracy and generation quality

• Participate in developing and testing MCP (Model Context Protocol) application integration solutions

• Develop practical application features using mainstream AI frameworks like Langchain, LlamaIndex, etc.

• Participate in model fine-tuning experiments and prompt engineering optimization

• Assist in developing AI Agent systems, learn multi-agent collaboration and workflow orchestration

• Participate in vector database integration for semantic search functionality

What we need to see:

• Pursuing a BS/MS degree from EE/CS or related majors from a prestigious university.

• Familiarity with verification methodology, tools, and flow

• Understanding of front-end ASIC design flow, including RTL design, synthesis, and timing analysis

• Proficiency in Python/Perl/JavaScript is a plus

• Proficient in English (both written and spoken) and excellent communication skills,Outstanding analytical and problem-solving skills

• Strong teamwork spirit and the ability to collaborate easily with team members

• Proficient in Python with good coding practices

• Understand basic data structures and algorithms

• Understand basic principles and applications of Large Language Models (LLMs)

• Basic knowledge of RAG, Agent, Prompt Engineering concepts

• Experience using at least one LLM API (OpenAI, Claude, etc.)

Ways to stand out from the crowd:

• AI Framework Experience**: Developed small projects or demos using Langchain, LlamaIndex, etc.

• RAG Practice**: Understand RAG principles, completed related course or personal projects

• Vector Databases**: Exposure to Milvus, ChromaDB, Faiss, Pinecone, or similar databases

• Model Fine-tuning**: Experience with fine-tuning, familiar with parameter-efficient methods like LoRA

NVIDIA is widely considered to be one of the technology world’s most desirable employers. We have some of the most experienced and talented individuals in the world working for us. If you're creative and autonomous, we want to hear from you!