AI/ML Internship

Onto Innovation•Milpitas, CA

About The Position

Onto Innovation is a leader in process control, combining global scale with an expanded portfolio of leading-edge technologies that include: 3D metrology spanning the chip from nanometer-scale transistors to micron-level die-interconnects; macro defect inspection of wafers and packages; metal interconnect composition; factory analytics; and lithography for advanced semiconductor packaging. Our breadth of offerings across the entire semiconductor value chain helps our customers solve their most difficult yield, device performance, quality, and reliability issues. Onto Innovation strives to optimize customers’ critical path of progress by making them smarter, faster and more efficient. Job Summary & Responsibilities Job Summary MBU (Metrology Business Unit) is seeking a highly motivated AI/ML Intern to support validation and optimization of a Retrieval-Augmented Generation (RAG)-based AI system for AiD and N2K product ecosystems. The intern will work on real-world semiconductor software challenges, focusing on improving AI-driven knowledge retrieval for faster resolution of field escalations. This role offers hands-on experience with production-scale LLM systems and exposure to cross-functional engineering environments.

Requirements

Currently pursuing a Bachelor's or Master's degree in Computer Science, AI/ML, Data Science, or related field
Strong programming skills in Python
Understanding of machine learning, NLP, or large language models
Familiarity with data analysis and problem-solving techniques
Strong communication and documentation skills

Nice To Haves

Experience with LLM frameworks (e.g., OpenAI, LangChain, Hugging Face)
Knowledge of vector databases (e.g., FAISS, Pinecone)
Experience with Retrieval-Augmented Generation (RAG) concepts
Exposure to cloud platforms (Azure preferred)
Interest in semiconductor or industrial software systems

Responsibilities

Validate performance of RAG-based LLM models using real field escalation scenarios
Analyze and structure internal data sources including logs, knowledge base, and support documentation
Develop and optimize retrieval pipelines including embeddings and indexing strategies
Improve prompt engineering techniques to enhance response accuracy and relevance
Benchmark RAG models against baseline LLM approaches
Identify data gaps and recommend improvements for knowledge coverage
Collaborate with software, applications, and product teams to align solutions with business needs
Document findings and present results to stakeholders