Summer Internship: Machine Learning/Deep Learning, Global Digital Health Intern (Hybrid - San Carlos, CA)

BeiGene•San Carlos, CA

1d•Hybrid

About The Position

BeOne Medicines is seeking an exceptional MS/PhD intern in Machine Learning/Deep Learning to help define and build a high-impact modeling capability in Hematology and Oncology. This is a high-ownership internship for a candidate who wants to do meaningful technical work at the intersection of AI and disease-area strategy. The intern will work directly with our Global Digital Health leadership and scientific leaders and partner with cross-functional stakeholders to frame important scientific or clinical questions, translate into machine learning problems, and co-lead the development of initial models or modeling frameworks. This is a greenfield opportunity to help shape how advanced AI methods can support decision-making in a clinically important area.

Requirements

Currently enrolled in a MS/PhD program in Computer Science, Statistics, Biomedical Informatics, Computational Biology, or a related quantitative field.
Strong foundation in machine learning and deep learning; and strong programming skills in Python.
Hands-on experience with one or more modern ML/DL frameworks such as PyTorch, TensorFlow, or JAX.
Experience designing, training, evaluating, and debugging models on real-world datasets.
Candidates must be legally authorized to work in the United States for the duration of the internship.

Nice To Haves

Publication experience in top-tier peer-reviewed venues or major journals/conferences in machine learning, deep learning, AI, computational biology, or related fields.
Research experience in machine learning, deep learning, generative AI, representation learning, multimodal learning, or related areas.
Prior work with biomedical, clinical, molecular, imaging, or other life sciences datasets.
Strong interest in oncology, translational medicine, or applied AI in healthcare.

Responsibilities

Translate scientific questions into a concrete modeling problem, including hypothesis, target variable, evaluation criteria, and success metrics.
Audit, curate, and structure relevant datasets, which may include structured, unstructured, or multimodal biomedical data.
Design, train, benchmark, and refine machine learning/deep learning models using modern methods appropriate to clinical and scientific problems, such as gradient boosting, deep neural networks, representation learning, transfer learning, or foundation-model-based approaches.
Deliver clean code, experiment documentation, and a final technical readout with recommendations for next steps beyond the internship.