AI System Development Intern at ASUS in Fremont, CA

Summary: ASUS is a technology company seeking an AI System Development Intern to support the research, design, and implementation of localized Large Language Model (LLM) solutions. The intern will collaborate with IT teams, assist in system design, and support the development of automated Q&A systems to enhance the corporate IT Knowledge Base. Responsibilities: - Collaborate with IT teams to identify key knowledge domains and document functional requirements for the automated Q&A system - Assist in designing system architectures for local LLM deployment, including RAG (Retrieval-Augmented Generation) workflows and web agent integration - Support the development team in implementing web agents and integrating LLM APIs with internal IT systems - Organize and process unstructured IT documentation into vector databases to facilitate efficient semantic search and retrieval - Participate in fine-tuning and filtering LLM output to improve the precision and reliability of technical answers - Prepare and maintain documentation for AI workflows, including system specifications and user guides for the IT Knowledge Base - Participate in unit and integration testing, specifically focusing on the accuracy of LLM responses and the stability of web agent interactions - Work closely with senior developers and system analysts to ensure seamless integration of AI components into the existing IT infrastructure Required Qualifications: - Currently pursuing a BS or MS degree in Computer Science, Data Science, Electrical/Computer Engineering, or a related field - Academic or project experience involving LLMs, Machine Learning, or Natural Language Processing (NLP) - Strong analytical skills to translate complex IT troubleshooting processes into effective AI prompts and logic - Familiarity with Python, LLM frameworks (such as LangChain or Semantic Kernel), and database concepts - Knowledge of vector databases (e.g., Pinecone, Milvus, or FAISS) is highly advantageous - Understanding of RAG architecture, prompt engineering, and basic model fine-tuning techniques - Effective verbal and written communication skills to document AI logic and interact with technical teams - Keen attention to detail in verifying the accuracy of AI-generated content and troubleshooting logic errors in web agents - Flexibility to adapt to the rapidly evolving AI landscape and changing project requirements in a dynamic environment Preferred Qualifications: - Experience with web scraping or agentic workflows is a plus Required Skills: Python, Large Language Models (LLM), LLM Frameworks, LangChain, Semantic Kernel, Vector Databases, Pinecone, Milvus, FAISS, Retrieval-Augmented Generation (RAG), Prompt Engineering, Model Fine-Tuning, Machine Learning, Natural Language Processing (NLP), Web Scraping, Agentic Workflows, Analytical Skills Benefits: Bonuses, Medical, Dental, Vision, Life insurance, AD&D insurance, Paid Time Off, EAP, 401(k)