2026 Summer Intern - AI for Drug Discovery

Roche•South San Francisco, CA

2d•$50 - $50•Onsite

About The Position

2026 Summer Intern - AI for Drug Discovery Department Summary We seek a highly motivated research intern to join the Small Molecule Artificial Intelligence for Drug Discovery Team at Prescient Design within Genentech Research and Early Development (gRED). As a successful candidate, you will develop and apply novel machine learning methods, specifically protein-ligand binding affinity models, to small-molecule drug discovery tasks, including molecular design. Our team fosters a collaborative approach that stimulates innovative thinking and the potential for creative breakthroughs at the forefront of ML research. This internship position is located on-site in South San Francisco. The Opportunity You will evaluate the impact of recent advances of predictive models for molecular potency/affinity prediction Application of predictive models that place a variety of physical priors on the problem of potency prediction: GNNs, transformers, geometric neural networks, etc. Collaborate closely on machine learning projects for drug discovery with machine learning scientists, research engineers, computational biologists, chemists, and biologists. Develop and execute a research agenda focused on advancing potency modeling and better understanding the limitations different inductive biases place on the problem. Report and present research findings and developments including status and results clearly, verbally and in writing (publishing in top-tier machine learning or chemistry venues). Program Highlights Intensive 12-weeks, full-time (40 hours per week) paid internship. Program start dates are in May/June A stipend, based on location, will be provided to help alleviate costs associated with the internship. Ownership of challenging and impactful business-critical projects. Work with some of the most talented people in the biotechnology industry. Who We Are Genentech, a member of the Roche group and founder of the biotechnology industry, is dedicated to pursuing groundbreaking science to discover and develop medicines for people with serious and life-threatening diseases. To solve the world's most complex health challenges, we ask bigger questions that challenge our industry and the boundaries of science to transform society. Our transformational discoveries include the first targeted antibody for cancer and the first medicine for primary progressive multiple sclerosis. The next step is yours. To apply today, click on the "Apply for this job" button.

Requirements

Must be pursuing a PhD (enrolled student).
Physical or life sciences (Chemistry, Biology, Physics) or quantitative field (Computer Science, Statistics, Mathematics).
Strong research interest in geometric neural networks, graph neural networks, representation learning, and chemical properties prediction.
Fluent in Python and experience with modern Python frameworks for deep learning (e.g. PyTorch or TensorFlow).
Interest in binding affinity prediction and pose generation for molecular design.

Nice To Haves

Excellent communication, collaboration, and interpersonal skills.
Complements our culture and the standards that guide our daily behavior & decisions: Integrity, Courage, and Passion.
Demonstrated computational research experience, as evidenced by publications, public code repositories, or equivalent.
Familiarity with pose generation methods, both classical and data-driven (e.g., docking, molecular dynamics, AlphaFold3, etc.)
Experience with one or more cheminformatics or drug discovery toolkits (e.g. OpenEye, Schrodinger, RDKit, OpenBabel).
Experience working with large chemical and biological datasets, including sequence, text, graph, and structure-based data.

Responsibilities

Evaluate the impact of recent advances of predictive models for molecular potency/affinity prediction
Application of predictive models that place a variety of physical priors on the problem of potency prediction: GNNs, transformers, geometric neural networks, etc.
Collaborate closely on machine learning projects for drug discovery with machine learning scientists, research engineers, computational biologists, chemists, and biologists.
Develop and execute a research agenda focused on advancing potency modeling and better understanding the limitations different inductive biases place on the problem.
Report and present research findings and developments including status and results clearly, verbally and in writing (publishing in top-tier machine learning or chemistry venues).