Machine Learning / Clinical AI Summer… at CareDx, Inc. · Brisbane

Summary: CareDx, Inc. is a leading precision medicine solutions company focused on the discovery, development, and commercialization of clinically differentiated, high-value healthcare solutions for transplant patients. This internship is designed as an immersive, learning-driven experience for students who want to deepen their skills in machine learning and large language models while working with real-world healthcare data. Responsibilities: - Assist with applying machine learning and LLM-based methods to unstructured clinical data such as clinical notes, PDFs, and scanned documents - Support information extraction tasks including classification, entity tagging, summarization, and basic data analysis under guidance from senior team members - Help prepare and preprocess text, PDF, and image data for modeling, including data cleaning and organization - Assist with building and maintaining simple pipelines that incorporate OCR and NLP tools for document processing - Participate in testing and evaluating model outputs using predefined metrics and evaluation frameworks - Collaborate with data scientists, engineers, and clinical stakeholders to understand clinical workflows and modeling goals - Clearly document experiments, results, and observations for internal sharing and knowledge transfer - Follow data privacy, security, and compliance requirements when working with healthcare data Required Qualifications: - Currently pursuing a bachelor's degree in computer science, Data Science, Biomedical Engineering, Artificial Intelligence, or related field - Coursework or academic projects in machine learning, data science, or artificial intelligence - Programming experience in Python and familiarity with foundational ML libraries (e.g., PyTorch, TensorFlow, scikit‑learn, Hugging Face) - Introductory understanding of natural language processing concepts - Interest in healthcare, clinical data, or biomedical applications of AI - Openness to feedback, enthusiasm for learning, and a collaborative mindset Preferred Qualifications: - Class projects or internship experience working with unstructured data such as text, PDFs, or images - Exposure to OCR tools, document processing, or basic computer vision concepts - Familiarity with large language models through coursework, projects, or experimentation - Interest in healthcare or biomedical data (prior domain knowledge not required) - Strong organization and communication skills Required Skills: Machine Learning, Python Important Skills: Natural Language Processing, Data Science, Large Language Models Nice-to-Have Skills: OCR Tools, Document Processing, Communication Skills, Collaboration Mindset Benefits: May be eligible for additional discretionary bonuses/incentives and restricted stock units