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

‍